125 results on '"Radfar, A."'
Search Results
2. End-to-End Spoken Language Understanding Using Joint CTC Loss and Self-Supervised, Pretrained Acoustic Encoders
- Author
-
Wang, Jixuan, primary, Radfar, Martin, additional, Wei, Kai, additional, and Chung, Clement, additional
- Published
- 2023
- Full Text
- View/download PDF
3. Excellent Responsivity and Low Dark Current Obtained with Metal-Assisted Chemical Etched Si Photodiode
- Author
-
Kexun Chen, Olli E. Setälä, Xiaolong Liu, Behrad Radfar, Toni P. Pasanen, Michael D. Serué, Juha Heinonen, Hele Savin, Ville Vähänissi, Hele Savin Group, Department of Electronics and Nanoengineering, ElFys Inc., Aalto-yliopisto, and Aalto University
- Subjects
responsivity ,MACE ,Si ,Electrical and Electronic Engineering ,photodetector ,Instrumentation - Abstract
Metal-assisted chemical etched (MACE; also known as MacEtch or MCCE) nanostructures are utilized widely in the solar cell industry due to their excellent optical properties combined with a simple and cost-efficient fabrication process. The photodetection community, on the other hand, has not shown much interest toward MACE due to its drawbacks, including insufficient surface passivation, increased junction recombination, and possible metal contamination, which are especially detrimental to p-n photodiodes. Here, we aim to change this by demonstrating how to fabricate high-performance MACE p-n photodiodes with above 90% external quantum efficiency (EQE) without external bias voltage at 200-1000 nm and dark current less than 3 nA/cm2 at -5 V using industrially applicable methods. The key is to utilize an induced junction created by an atomic layer deposited (ALD) highly charged Al2O3 thin film that simultaneously provides efficient field-effect passivation and full conformality over the MACE nanostructures. Achieving close to ideal performance demonstrates the vast potential of MACE nanostructures in the fabrication of high-performance low-cost p-n photodiodes.
- Published
- 2023
4. Sub-8-Bit Quantization for On-Device Speech Recognition: A Regularization-Free Approach
- Author
-
Zhen, Kai, primary, Radfar, Martin, additional, Nguyen, Hieu, additional, Strimel, Grant P., additional, Susanj, Nathan, additional, and Mouchtaris, Athanasios, additional
- Published
- 2023
- Full Text
- View/download PDF
5. Multi-Task RNN-T with Semantic Decoder for Streamable Spoken Language Understanding
- Author
-
Fu, Xuandi, Chang, Feng-Ju, Radfar, Martin, Wei, Kai, Liu, Jing, Strimel, Grant P., and Sathyendra, Kanthashree Mysore
- Subjects
FOS: Computer and information sciences ,Sound (cs.SD) ,Computer Science - Computation and Language ,Audio and Speech Processing (eess.AS) ,FOS: Electrical engineering, electronic engineering, information engineering ,Computation and Language (cs.CL) ,Computer Science - Sound ,Electrical Engineering and Systems Science - Audio and Speech Processing - Abstract
End-to-end Spoken Language Understanding (E2E SLU) has attracted increasing interest due to its advantages of joint optimization and low latency when compared to traditionally cascaded pipelines. Existing E2E SLU models usually follow a two-stage configuration where an Automatic Speech Recognition (ASR) network first predicts a transcript which is then passed to a Natural Language Understanding (NLU) module through an interface to infer semantic labels, such as intent and slot tags. This design, however, does not consider the NLU posterior while making transcript predictions, nor correct the NLU prediction error immediately by considering the previously predicted word-pieces. In addition, the NLU model in the two-stage system is not streamable, as it must wait for the audio segments to complete processing, which ultimately impacts the latency of the SLU system. In this work, we propose a streamable multi-task semantic transducer model to address these considerations. Our proposed architecture predicts ASR and NLU labels auto-regressively and uses a semantic decoder to ingest both previously predicted word-pieces and slot tags while aggregating them through a fusion network. Using an industry scale SLU and a public FSC dataset, we show the proposed model outperforms the two-stage E2E SLU model for both ASR and NLU metrics., Accepted at ICASSP 2022
- Published
- 2022
6. A Neural Prosody Encoder for End-to-End Dialogue Act Classification
- Author
-
Kai Wei, Dillon Knox, Martin Radfar, Thanh Tran, Markus Muller, Grant P. Strimel, Nathan Susanj, Athanasios Mouchtaris, and Maurizio Omologo
- Published
- 2022
7. Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding
- Author
-
Bhuvan Agrawal, Markus Muller, Samridhi Choudhary, Martin Radfar, Athanasios Mouchtaris, Ross McGowan, Nathan Susanj, and Siegfried Kunzmann
- Published
- 2022
8. A Neural Prosody Encoder for End-to-End Dialogue Act Classification
- Author
-
Wei, Kai, primary, Knox, Dillon, additional, Radfar, Martin, additional, Tran, Thanh, additional, Muller, Markus, additional, Strimel, Grant P., additional, Susanj, Nathan, additional, Mouchtaris, Athanasios, additional, and Omologo, Maurizio, additional
- Published
- 2022
- Full Text
- View/download PDF
9. Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding
- Author
-
Agrawal, Bhuvan, primary, Muller, Markus, additional, Choudhary, Samridhi, additional, Radfar, Martin, additional, Mouchtaris, Athanasios, additional, McGowan, Ross, additional, Susanj, Nathan, additional, and Kunzmann, Siegfried, additional
- Published
- 2022
- Full Text
- View/download PDF
10. Graph Signal Processing, Graph Neural Network and Graph Learning on Biological Data: A Systematic Review.
- Author
-
Li, Rui, Yuan, Xin, Radfar, Mohsen, Marendy, Peter, Ni, Wei, O'Brien, Terrence J., and Casillas-Espinosa, Pablo
- Abstract
Graph networks can model data observed across different levels of biological systems that span from population graphs (with patients as network nodes) to molecular graphs that involve omics data. Graph-based approaches have shed light on decoding biological processes modulated by complex interactions. This paper systematically reviews graph-based analysis methods of Graph Signal Processing (GSP), Graph Neural Networks (GNNs) and graph topology inference, and their applications to biological data. This work focuses on the algorithms of graph-based approaches and the constructions of graph-based frameworks that are adapted to a broad range of biological data. We cover the Graph Fourier Transform and the graph filter developed in GSP, which provides tools to investigate biological signals in the graph domain that can potentially benefit from the underlying graph structures. We also review the node, graph, and interaction oriented applications of GNNs with inductive and transductive learning manners for various biological targets. As a key component of graph analysis, we provide a review of graph topology inference methods that incorporate assumptions for specific biological objectives. Finally, we discuss the biological application of graph analysis methods within this exhaustive literature collection, potentially providing insights for future research in biological sciences. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
11. Context-Aware Transformer Transducer for Speech Recognition
- Author
-
Chang, Feng-Ju, primary, Liu, Jing, additional, Radfar, Martin, additional, Mouchtaris, Athanasios, additional, Omologo, Maurizio, additional, Rastrow, Ariya, additional, and Kunzmann, Siegfried, additional
- Published
- 2021
- Full Text
- View/download PDF
12. Millisecond-Level Minority Carrier Lifetime in Femtosecond Laser-Textured Black Silicon.
- Author
-
Liu, Xiaolong, Radfar, Behrad, Chen, Kexun, Palikko, Elmeri, Pasanen, Toni P., Vahanissi, Ville, and Savin, Hele
- Abstract
Femtosecond laser-textured black silicon (fs-bSi) is known to suffer from heavy minority carrier recombination resulted from laser irradiation. In this letter, we demonstrate that the thermal annealing step, generally used to recover the crystal damage, could improve the minority carrier lifetime of the fs-bSi wafers only from $8 \mu \text{s}$ to $12 \mu \text{s}$ , even when using as high temperature as 800 °C. However, with an optimized wet chemical etching process, we obtain a high minority carrier lifetime of 2 ms without sacrificing the optical properties of the samples, i.e., the absorptance remains above 90% in the studied wavelength range (250–1100 nm). Increasing the etching time further leads to a total recovery of the lifetime up to 10.5 ms, which proves that the damage originating from the fs-laser texturing extends only to the near-surface layer (a few $\mu \text{m}$) of silicon. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
13. Perspectives on Black Silicon in Semiconductor Manufacturing: Experimental Comparison of Plasma Etching, MACE, and Fs-Laser Etching.
- Author
-
Liu, Xiaolong, Radfar, Behrad, Chen, Kexun, Setala, Olli E., Pasanen, Toni P., Yli-Koski, Marko, Savin, Hele, and Vahanissi, Ville
- Subjects
- *
PLASMA etching , *ETCHING , *SEMICONDUCTOR manufacturing , *SILICON , *SOLAR cells , *OPTOELECTRONIC devices - Abstract
In semiconductor manufacturing, black silicon (bSi) has traditionally been considered as a sign of unsuccessful etching. However, after more careful consideration, many of its properties have turned out to be so superior that its integration into devices has become increasingly attractive. In devices where bSi covers the whole wafer surface, such as solar cells, the integration is already rather mature and different bSi fabrication technologies have been studied extensively. Regarding the integration into devices where bSi should cover only small selected areas, existing research focuses on device properties with one specific bSi fabrication method. Here, we fabricate bSi patterns with varying dimensions ranging from millimeters to micrometers using three common bSi fabrication techniques, i.e., plasma etching, metal-assisted chemical etching (MACE) and femtosecond-laser etching, and study the corresponding fabrication characteristics and resulting material properties. Our results show that plasma etching is the most suitable method in the case of $\mu \text{m}$ -scale devices, while MACE reaches surprisingly almost the same performance. Femtosecond-laser has potential due to its maskless nature and capability for hyperdoping, however, in this study its moderate accuracy, large silicon consumption and spreading of the etching damage outside the bSi region leave room for improvement. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
14. End-to-End Multi-Channel Transformer for Speech Recognition
- Author
-
Chang, Feng-Ju, primary, Radfar, Martin, additional, Mouchtaris, Athanasios, additional, King, Brian, additional, and Kunzmann, Siegfried, additional
- Published
- 2021
- Full Text
- View/download PDF
15. Speech Emotion Recognition Using Quaternion Convolutional Neural Networks
- Author
-
Muppidi, Aneesh, primary and Radfar, Martin, additional
- Published
- 2021
- Full Text
- View/download PDF
16. Low Phase Noise Oscillator Design Using Degenerate Band Edge Ladder Architectures.
- Author
-
Radfar, Mohammad, Oshmarin, Dmitry, Othman, Mohamed A. K., Green, Michael M., and Capolino, Filippo
- Abstract
A new approach based on a strong degeneracy state to design oscillators that exhibit low phase noise and low power consumption is presented. A 100-MHz oscillator is designed using a periodic structure based on a degenerate band edge that is augmented with an NMOS cross-coupled pair. The analysis and simulation results show 16 dB phase noise improvement compared to oscillators based on a conventional single-ladder periodic structure. It is also shown that this oscillator dissipates less power than a conventional LC oscillator that requires a buffer to drive a $50\Omega $ load. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
17. A Low-Power Low-Voltage Dynamic Comparator in 180nm CMOS Technology
- Author
-
Ghaziani, Niloofar, primary, Radfar, Sara, additional, Bastan, Yasin, additional, Amiri, Parviz, additional, and Maghami, Mohammad Hossein, additional
- Published
- 2020
- Full Text
- View/download PDF
18. Harnessing Carrier Multiplication in Silicon Solar Cells Using UV Photons.
- Author
-
Chen, Kexun, Setala, Olli E., Radfar, Behrad, Kroth, Udo, Vahanissi, Ville, and Savin, Hele
- Abstract
Silicon solar cells are known to suffer from poor emitter performance that is seen as reduced external quantum efficiency at wavelengths below 500 nm. This is due to common tradeoff between electrical and optical performance. Here we demonstrate that no such tradeoff is needed when optimized boron implantation parameters are combined with non-reflective nanostructures and atomic layer deposited Al2O3 surface passivation. As a result, in our solar cells the external quantum efficiency actually increases with decreasing wavelength and reaches even above 100% at short wavelengths. This result indicates that carrier multiplication caused by absorption of high energy photons could be utilized for energy production in solar cells. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
19. Dual-Polarized Slot Antenna for Full-Duplex Systems With High Isolation.
- Author
-
Nguyen, Anh-Ngoc, Hoang Le, Viet, Nguyen-Trong, Nghia, Radfar, Mohsen, Ebrahimi, Amir, Phan, Khoa, and Desai, Aniruddha
- Subjects
POWER dividers ,ELECTRIC lines ,ANTENNA feeds ,SLOT antennas ,ANTENNAS (Electronics) ,COPLANAR waveguides - Abstract
A single-layered slot antenna system working at 5.8 GHz Industrial, Scientific and Medical (ISM) band is proposed for in-band full duplex (IBFD) operation applications without the use of a coupler. First, high isolation is achieved by strong separation of even- and odd-mode feeds. The microstrip-coupled coplanar waveguide (CPW) is used at Port 1 (TX port) to excite a stepped-slot antenna in the CPW odd mode. On the opposite side, a microstrip T-junction power divider is employed at Port 2 (RX port) to feed two offset-fed stepped-slot antennas in even mode. Second, isolation is further improved by 30 dB by using a lumped capacitor at the termination of the CPW. The measured isolation between the two ports is about 50 dB across the bandwidth. The measured −10 dB bandwidth of Port 1 is 0.49 GHz (8.5%), while that of Port 2 is 1.06 GHz (18.3%). The gains of TX and RX antennas are 5.4 and 5.8 dBi at 5.8 GHz. The proposed antenna can also be deployed as a dual-polarized antenna. Mathematical analysis and equivalent transmission line circuit models are provided to give physical insight into the working principals of the antenna with validation from ANSYS HFSS simulation. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
20. An Ultra-Low-Voltage Sub-Threshold Pseudo-Differential CMOS Schmitt Trigger
- Author
-
Parviz Amiri, Sara Radfar, Ali Nejati, Sotoudeh Hamedi-Hagh, Mehdi Nasrollahpour, and Yasin Bastan
- Subjects
Physics ,0209 industrial biotechnology ,Hardware_MEMORYSTRUCTURES ,business.industry ,020208 electrical & electronic engineering ,Transistor ,Electrical engineering ,Hardware_PERFORMANCEANDRELIABILITY ,02 engineering and technology ,law.invention ,Threshold voltage ,Hysteresis ,020901 industrial engineering & automation ,CMOS ,Hardware_GENERAL ,law ,Schmitt trigger ,Hardware_INTEGRATEDCIRCUITS ,0202 electrical engineering, electronic engineering, information engineering ,Differential (infinitesimal) ,business ,Low voltage ,Voltage - Abstract
In this paper, an ultra-low-voltage, low-power pseudo-differential CMOS Schmitt trigger is presented. The bulk-driven and sub-threshold techniques are used to achieve low-voltage and low-power circuit. The regenerative current feedback is applied to provide the hysteresis of the op-amp based Schmitt trigger. The proposed Schmitt trigger is designed and simulated in 0.18 μm CMOS technology and it is operated in 0.4 V supply voltage with 150 nW power consumption.
- Published
- 2018
21. Low-Power Area-Efficient LDO With Loop-Gain and Bandwidth Enhancement Using Non-Dominant Pole Movement Technique for IoT Applications.
- Author
-
Nakhlestani, Amir, Kaveri, Shridevi Venkatesh, Radfar, Mohsen, and Desai, Aniruddha
- Abstract
A new Low Drop-Out (LDO) voltage regulator with off-chip capacitor for low power applications is presented. The LDO takes advantage of non-dominant pole movement technique to improve loop-gain and Unity Gain Frequency (UGF). Tangible improvements were obtained while supporting a large load capacitor and low-power consumption. The proposed LDO 1) consumes low quiescent current (47.3% current efficiency (CE) at $10~\mu \text{A}$ load current bias circuit inclusive), 2) is area-efficient (no multi-gain amplifiers), and 3) enjoys a short response time in the active-mode with its adaptive bandwidth expansion and loop-gain enhancement technique, while 4) maintaining 99.94% CE in the full-load condition. A prototype chip with TSMC 180 nm CMOS technology was fabricated for detailed characterisation. The measured output voltage of the LDO was 1.65 V with 1.8 V input, consuming $11~\mu \text{A}$ quiescent current including the bias circuit current. The load regulation was 10 mV when load current changes from 30 nA to 50 mA with fall and rise time of 10ns. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
22. An LC voltage-controlled oscillator with supply sensitivity compensation method
- Author
-
Michael M. Green and M.H. Radfar
- Subjects
Materials science ,Capacitive sensing ,020208 electrical & electronic engineering ,02 engineering and technology ,020202 computer hardware & architecture ,Compensation (engineering) ,Power (physics) ,Voltage-controlled oscillator ,Control theory ,Phase noise ,Hardware_INTEGRATEDCIRCUITS ,0202 electrical engineering, electronic engineering, information engineering ,Electronic engineering ,Sensitivity (control systems) ,Frequency modulation ,Jitter - Abstract
The mechanism by which the frequency of an LC VCO is sensitive to the power supply is analyzed. It is shown that variations in both the common-mode and differential-mode components can give rise to periodic jitter in the presence of supply variations due to capacitive nonlinearities. A new compensation method that reduces this sensitivity is presented. Simulations are shown verifying that this method can reduce the periodic jitter by more than 80%.
- Published
- 2017
23. Wideband Compact Triangle-Slot Antenna With Out-of-Band Rejection.
- Author
-
Nguyen, Ngoc-Anh, Radfar, Mohsen, Ebrahimi, Amir, Ngo, Vu-Duc, Bervan, Aidin, Le, Viet Hoang, and Desai, Aniruddha
- Abstract
A wideband and compact triangle-slot antenna with out-of-band rejection is proposed. The antenna covers the whole C-band (4–8 GHz) including the 5.8 GHz ISM and sub-6 GHz band of 5G. First, a right-angled triangle-slot antenna is developed from a rotated square-slot antenna with a 50% size miniaturization. Then, a defected ground slot (DGS) and a thin microstrip line section are integrated into the antenna to improve the out-of-band rejection. This prevents the noise and unwanted interference to the receiver and effectively suppresses the high-order harmonics from the transmitter. Importantly, the added DGS and thin microstrip line increases the bandwidth up to 5.51 GHz (82.7% fractional bandwidth) and reduces the antenna size. Finally, by adding matching elements using stacked rectangular slot principle, the antenna size is reduced furthermore, leading to a total 60% reduction in size. The final ground size is 32 × 32 mm, which is suitable to be integrated into portable devices. The return loss is measured up to the third harmonic of the highest working frequency and compared with the reference triangle-slot antenna to validate the rejection concept. The out-of-band return loss remains smaller than 1.2 dB up to 26.5 GHz. The maximum improvement of return loss is 33.3 dB at 26.4 GHz, from 34.4 dB of the reference antenna to 1.1 dB of the proposed antenna. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
24. An Ultra-Low-Voltage Sub-Threshold Pseudo-Differential CMOS Schmitt Trigger
- Author
-
Bastan, Yasin, primary, Nejati, Ali, additional, Radfar, Sara, additional, Amiri, Parviz, additional, Nasrollahpour, Mehdi, additional, and Hamedi-Hagh, Sotoudeh, additional
- Published
- 2018
- Full Text
- View/download PDF
25. Battery Management Technique to Reduce Standby Energy Consumption in Ultra-Low Power IoT and Sensory Applications.
- Author
-
Radfar, Mohsen, Nakhlestani, Amir, Viet, Hoang Le, and Desai, Aniruddha
- Subjects
- *
ENERGY consumption , *ELECTRIC batteries , *ARCHITECTURAL design , *RADIO frequency , *ELECTRIC vehicle batteries , *THRESHOLD voltage - Abstract
In this paper, we present a battery management technique that significantly increases the battery lifetime of event-based devices that are predominantly in standby mode without requiring off or on chip large power switches. The proposed technique uses a novel battery management technique to remove Wake-Up Receiver (WUR) Low Drop-Out (LDO) unit, while causing minimal change to the system’s power supply configuration. This technique manages the system so that it can wake up to a normal battery configuration while sleeping in a different battery set-up. This, as a result, drops standby power consumption significantly, making the proposed technique suitable for IoT sensors and, in general, event-based devices. Battery management comprises of voltage level detector, switches for changing battery configuration, and voltage level shifters. The design was applied to an active Radio Frequency Identification (RFID) tag with an embedded WUR and fabricated using TSMC 180nm technology. Measurements on the test chip showed that the proposed architecture and design leads to 80% standby energy saving, prolonging overall (active plus standby) battery’s lifetime by 2.5 times while having negligible area overhead. The advantages and disadvantages of the proposed technique are also presented and discussed. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
26. Power delivery solutions in 3-D processor-DRAM systems in presence of hot spots
- Author
-
Reza Sarvari, Farzad Radfar, and Masoud Zabihi
- Subjects
Engineering ,business.industry ,Power module ,Embedded system ,Electrical engineering ,Power integrity ,Hot spot (veterinary medicine) ,Solid modeling ,business ,Noise (electronics) ,Dram ,Die (integrated circuit) ,Power (physics) - Abstract
An important application of 3-D integration technology is stacked processor-DRAM systems. One of the major design issues in 3-D processor-DRAM stacks is power delivery. Presence of hot spots, high density power regions, in processor die poses serious challenges to the design of power distribution network (PDN). In this paper, we investigate solutions to ensure power integrity in the hot spot regions.
- Published
- 2014
27. Comparison between optimal interconnection network in different 2D and 3D NoC structures
- Author
-
Reza Sarvari, Masoud Zabihi, and Farzad Radfar
- Subjects
Router ,Interconnection ,Engineering ,business.industry ,Mesh networking ,Torus ,Bisection bandwidth ,Hypercube ,Parallel computing ,Chip ,Network topology ,business - Abstract
The current article studies optimal intercore interconnect network in a NoC structure for 2D and 3D mesh, torus and hypercube topologies. Optimal wire width/spacing is calculated by numerically maximizing bandwidth times the reciprocal delay, which depends on the technology node and hop length. Through 3D integration and increasing tiers, optimal interconnect width and spacing in torus and hypercube topologies will decrease. The core-to-core channel width in all topologies will be obtained by assigning 20% of the power consumption to the routers. By increasing number of cores, channel width will decrease due to reduced power consumption of each core. This is more in hypercube topology, due to the fact that the number of router ports will increase along with an increase in the number of cores. In terms of the worst case delay, mesh topology is worse than the two other topologies. Also it is not scalable due to the increase in the number of cores. In all topologies, power consumption of the chip and the worst case delay will decrease by 3D integration and utilizing more tiers. Mesh and torus topologies make the least and the most use of wiring area, respectively. Bisection bandwidth increases in all topologies by 3D integration.
- Published
- 2014
28. Data mining application for customer segmentation based on loyalty: An iranian food industry case study
- Author
-
Ali Hajiha, Samira Sarafi Malayeri, and Reza Radfar
- Subjects
Food industry ,Computer science ,business.industry ,media_common.quotation_subject ,k-means clustering ,Customer relationship management ,computer.software_genre ,Loyalty business model ,Market segmentation ,Loyalty ,Customer satisfaction ,Data mining ,Cluster analysis ,business ,computer ,media_common - Abstract
Data Mining (DM) is a powerful new technique to help companies discover the patterns and trends in their customers' preferences. It is also a well-known tool for customer relationship management (CRM). Data mining methodology has made a tremendous contribution for researchers wanting to extract hidden knowledge and information. This study has proposed a new procedure, based on an expanded RFM model, by including two additional parameters D and C. It constructs a model for clustering customer value based on RFMDC attributes and K-means algorithm. We evaluate the result and suggest suitable behavior policies for each cluster. The developed methodology has been implemented for Kalleh dairy company in Iran to illustrate the proposed procedure.
- Published
- 2011
29. Using AHP- COPRAS-G method for forest roads locating
- Author
-
Sarfaraz Hashemkhani Zolfani, Iman Radfar, Mehdi Shadifar, and Nahid Rezaeiniya
- Subjects
Geography ,Work (electrical) ,business.industry ,Environmental resource management ,Forest management ,Forest road ,Analytic hierarchy process ,business ,Multiple-criteria decision analysis ,Selection (genetic algorithm) - Abstract
Forest roads have an important role in the forest management and economic of countries. The Caspian forest is the most important forests region in Iran. It's so important to construction of forest roads in the best place that can be useful. Haraz region is located inMazandaran province that is near to Alborz Mountain. Selection the best place for construction of a road in forest is an important problem. For this research three place are considered for evaluating in Haraz region that including: Kelerd, Pelet Cheshme and Mangel. In this paper we applied hybrid MCDM methods for evaluating the regions. AHP applied for calculating the weight of each criterion and sub criterion and then COPRAS-G method applied for evaluating the places for selecting the best place for constructing the forest road. Result showed that Kelerd region in the best place for this work.
- Published
- 2011
30. A fuzzy MCDM approach for evaluating steel industry performance based on balanced scorecard: A case in Iran
- Author
-
Sarfaraz Hashemkhani Zolfani, Iman Radfar, and Heydar Amiran
- Subjects
Balanced scorecard ,Operations research ,Computer science ,Management science ,Fuzzy topsis ,Fuzzy set ,Rank (computer programming) ,Fuzzy number ,Multiple-criteria decision analysis ,Fuzzy logic ,Fuzzy mcdm - Abstract
The world manufacturing sector is facing massive challenges to survive in today's global and volatile market place. In an attempt to overcome these challenges, companies are adopting newer method to performance evaluation of industries and Small & Medium Size Enterprises (SME). The purpose of this study is to construct balanced score card (BSC) for steel industries. This research summarizes the evaluation indexes synthesized from the literatures relating to company performance first. Then, it introduces indexes for performance evaluation selected through experts' questionnaires. Furthermore, the relative weights of the chosen evaluation indexes are calculated by Fuzzy Analytic Hierarchy Process (FAHP). Weights of each criterion are described by linguistic terms which can be expressed in triangular fuzzy numbers. Fuzzy TOPSIS method, which is one of Multiple Criteria Decision Making (MCDM) analytical tool, is used to rank three mills' performance by calculating the distances to both the fuzzy positive-ideal solution (FPIS) and fuzzy negative-ideal solution (FNIS) simultaneously according to three case studies as empirical examples.
- Published
- 2011
31. Detection of upper airway narrowing via classification of LPC coefficients: Implications for obstructive sleep apnea diagnosis
- Author
-
Geoffrey R. Fernie, Hisham Alshaer, Martha Rodríguez García, M. Hossein Radfar, and T. Douglas Bradley
- Subjects
medicine.medical_specialty ,business.industry ,Speech recognition ,Speech sounds ,Sleep apnea ,Linear prediction coding ,medicine.disease ,Fluid shift ,Obstructive sleep apnea ,Patient diagnosis ,Internal medicine ,otorhinolaryngologic diseases ,Cardiology ,Medicine ,Airway ,business - Abstract
The similarities between unvoiced speech sounds and turbulent breath sounds were used to detect change in sound characteristics caused by narrowing of the upper airway (UA), similar to that occurring in obstructive sleep apnea (OSA). In 18 awake subjects, UA resistance (R AU ), an index of UA narrowing, was measured simultaneously with breath sounds recording. Linear Prediction Coding was applied on turbulent inspiratory sounds drawn from low and high R AU conditions and K-means was used to cluster the resulting coefficients. The resulting 2 clusters were tested for agreement with the underlying R AU status. Distinct clusters were formed when R UA increased relatively high but not in cases with lower rise in R UA (P
- Published
- 2011
32. MPtracker: A new multi-pitch detection and separation algorithm for mixed speech signals
- Author
-
Willy Wong, Richard M. Dansereau, M.H. Radfar, and Wai-Yip Chan
- Subjects
Computer science ,Computational auditory scene analysis ,Acoustics ,Speech recognition ,Audio time-scale/pitch modification ,Pitch detection algorithm ,Speech processing ,Signal ,Interpolation - Abstract
We present MPtracker, a new algorithm for tracking and separating the pitch frequencies of two speakers from their mixture. The pitch frequencies are detected by introducing a novel spectral distortion optimization which takes into account the sinusoidal modeling of the speech signal. The detected pitch frequencies are grouped, separated, and finally an interpolation method is applied to estimate missing pitch frequencies. We evaluated the performance of the proposed technique on 196 mixtures including 48 male-male, 48 female-female, and 96 male-female mixtures with target-to-interference ratios (TIR) ranging from 0 dB to +18 dB. The results show our simple but effective and fast technique significantly outperforms two widely-used approaches 1.
- Published
- 2011
33. Analysis of geometric and non-linear programming as optimization algorithms for low power VLSI circuits
- Author
-
Saadat Pour Mozafari, Jugdutt Singh, Kriyang Shah, and Mohsen Radfar
- Subjects
Very-large-scale integration ,Sequential logic ,Linear programming ,Computer science ,Algorithm design ,Geometric programming ,Algorithm ,Sequential quadratic programming ,Nonlinear programming - Abstract
In this paper, performance and accuracy of both General Geometric Programming (GGP) and non-linear programming (NLP) algorithms, for optimization of low power VLSI circuits, have been studied and compared. An optimization procedure based on GGP and logical effort method has been proposed and employed for optimization of variety of sequential logic circuits. The results were compared to the NLP algorithm of Sequential Quadratic Programming (SQP). Experiments showed that the GGP algorithm with Logical Effort method exhibits higher precision and acceptable speed compared to NLP algorithms. In fact, GGP is 9 orders of magnitude more accurate but 24× slower than NLP. However, with increasing circuit complexity the GGP does not degrade like NLP. Consequently, for complex circuits GGP is a good substitution for the speed of NLP algorithms and precision of simple LP (Linear Programming) algorithms, like Logical Effort.
- Published
- 2011
34. Proactive quality paint thickness control using ANFIS
- Author
-
Reza Radfar, Felora Ghoreishi, Javad Jassbi, Mahmood Alborzi, and Sohrab Khanmohammadi
- Subjects
Adaptive neuro fuzzy inference system ,Painting ,Computer science ,business.industry ,media_common.quotation_subject ,Control (management) ,Thin layer ,Automotive industry ,Process (computing) ,Paint shop ,Automotive engineering ,Quality (business) ,business ,media_common - Abstract
Automotive industries try to develop their technologies to improve quality and to minimize scrapes and wastes. In the paint shop vehicle, quality control generally relies on inspection. Industries try to develop their technologies to improve quality via proactive quality control. This paper investigates the predictability of the paint thickness to reduce defects, using ANFIS. A description of the automobile paint spray process is introduced and the inputs (as effective factors in paint spray process) are identified for each thin layer on a plate. A 50×80 sheet of metal is considered as a sample. In the present paper two models of ANFIS are presented. First model shows prediction of film thickness by using 6 inputs for bell, air layers, 7 input variables for dry film thickness or final paint thickness and 6 output points for three layers. Second model is predicting of paint appearing uniformity by average and standard deviation of film thickness.
- Published
- 2010
35. Study of products strategies in small and medium enterprises with implementing goal decision making
- Author
-
Abas Toloie Ashraghi, Sadegh Abedi, and Reza Radfar
- Subjects
Flexibility (engineering) ,business.industry ,Production manager ,Goal programming ,Production (economics) ,Factors of production ,Operations management ,Small and medium-sized enterprises ,business ,Industrial organization ,Decision-making models ,Outsourcing - Abstract
Nowadays scholars pay attention on SMEs because of more benefits in compare with Large Enterprises, such as: Value added, Innovation, Entrepreneurs and flexibility. But the other face of the coin is lack of production resources in SMEs. One of the solutions for this problem in researches has been used the potential in contractors companies, in form of out sourcing of activities and projects. In this paper we studied the production strategies in Iran' SMEs by identification and prioritizing the production factors and implementing the Goal Decision making model. Case studies consist of 5 different companies in the same field of production; approach us to analyzing the companies' situation. The paper presented the Matrix, base on results from models and case studies. This matrix suggested the different SME's situation for selected production strategies
- Published
- 2010
36. Scaled factorial hidden Markov models: A new technique for compensating gain differences in model-based single channel speech separation
- Author
-
Wai-Yip Chan, Richard M. Dansereau, Willy Wong, and M.H. Radfar
- Subjects
business.industry ,Iterative method ,Vector quantization ,Pattern recognition ,Viterbi algorithm ,Speech processing ,symbols.namesake ,Signal-to-noise ratio ,Source separation ,symbols ,Artificial intelligence ,Quadratic programming ,Hidden Markov model ,business ,Mathematics - Abstract
In model-based single channel speech separation, factorial hidden Markov models (FHMM) have been successfully applied to model the mixture signal Y(t) = X(t) + V(t) in terms of trained patterns of the speech signals X(t) and V(t). Nonetheless, when the test signals are scaled versions of the trained patterns (i.e. g x X(t) and g v V(t)), the performance of FHMM degrades significantly. In this paper, we introduce a modification to FHMM, called scaled FHMM, which compensates gain difference. In this technique, first, the scale factors are expressed in terms of the target-to-interference ratio (TIR). Then, an iteration quadratic optimization approach is coupled with FHMM to estimate TIR which with the decoded HMM sequences maximize the likelihood of the mixture signal. Experimental results, conducted on 180 mixtures with TIRs from 0 to 15 dB, show that the proposed technique significantly outperforms unscaled FHMM, and scaled/unscaled vector quantization speech separation techniques.
- Published
- 2010
37. Power delivery solutions in 3-D processor-DRAM systems in presence of hot spots
- Author
-
Zabihi, Masoud, primary, Radfar, Farzad, additional, and Sarvari, Reza, additional
- Published
- 2014
- Full Text
- View/download PDF
38. A novel analysis of rectangular dielectric waveguides using an interior-exterior integral equation technique
- Author
-
Reza Faraji-Dana and M.H. Radfar
- Subjects
Electric field ,Modal analysis ,Mathematical analysis ,Physics::Optics ,Boundary (topology) ,Dielectric ,Propagation constant ,Waveguide (optics) ,Integral equation ,Eigenvalues and eigenvectors ,Mathematics - Abstract
In this paper, we apply a modified integral equation technique to analyze rectangular dielectric waveguides with elimination of spurious modes. The two stage method applies interior problem by modal analysis to access the electric field in the waveguide in terms of the electric field on the boundaries. The exterior problem can be solved by integral equation technique to calculate the boundary fields regarding to interior fields. Using this approach, the eigen value problem can be formulated by finding the zeros of the relating determinant. Eliminating the spurious modes, the zeros of each mode are distinctly distinguishable. The consequent dispersion diagram is also has good agreements with the results of other methods for rectangular dielectric waveguide.
- Published
- 2009
39. Gain estimation in model-based single channel speech separation
- Author
-
Willy Wong, Richard M. Dansereau, Wai-Yip Chan, and M.H. Radfar
- Subjects
Signal-to-noise ratio ,Computational complexity theory ,business.industry ,Computer science ,Source separation ,Spectral density estimation ,Pattern recognition ,Artificial intelligence ,business ,Speech processing ,Energy (signal processing) ,Communication channel ,Separation process - Abstract
In most current model-based single channel separation techniques, it is assumed that the recording conditions are identical in the training phase and application phase. In this paper, we consider a general case in which training data and application data have different levels of energy and a technique is proposed to estimate the sources' gains which are required for the separation process. We use the periodogram of the speech signal as the selected feature for separation such that the sources' gains are estimated in terms of normalized periodograms of the sources and the mixture. The proposed technique is compared with a state-of-the-art technique which uses AR modeling of the speech signal and maximum likelihood for estimating gain and separating the sources. Experimental results show that our technique not only outperforms this technique in terms of SNR results and gain estimation accuracy but also reduces computational complexity.
- Published
- 2009
40. Modeling based on multi objective decision making for determining of goals' appropriate selection
- Author
-
Javad Jassbi, R. Radfar, and R. Babaali
- Subjects
Balanced scorecard ,Risk analysis (engineering) ,Ranking ,Point (typography) ,Fuzzy inference system ,Order (exchange) ,Management science ,Selection (linguistics) ,Strategic management ,Fuzzy logic ,Mathematics - Abstract
Resources limitations and requirements and representing a lot of objectives, have made inevitable the necessity of applying optimal and efficient available capabilities in each organization. For this reason, ranking of goals along with organizational goals in each organization cannot be avoided and also most of successful companies pay more attention to this point. But in achieving this objective considering goals and the decision maker conditions is mandatory. Therefore, presenting a scientific solution and appropriate model that can satisfy the relations between goals and limitations seems to be necessary. In the complicated situation, considering all components and factors in decision-making obliges us to create a balance between goals and effective factors in achieving them. In this condition, not only all of the components and environmental variables cannot be considered one dimensionally, but also the best solution is considering all conditions and goals and making a decision in order to succeed in the desired utility of them. These problems have caused the nature of decision making include so many ambiguities, from the simplest to the most complicated affairs, and caused decisions to be taken in a fuzzy environment. As fuzzy logic has several applications in making decision in uncertain and fuzzy environments, this paper intends to model one of the strict and sophisticated decisions of managers using a mathematical model based on fuzzy inference system, that is, analysis and determining ranking of goals, from the available list in which the maximum use of available resources, considering the existing limitations, can be reached.
- Published
- 2009
41. Using hybrid model with probability parameters to analysis queuing systems with layout constraints
- Author
-
Reza Radfar, Sadegh Abebi, Meysam Hadadi, and Masood Rafati
- Subjects
Queueing theory ,Operations research ,Markov chain ,Queue management system ,Computer science ,Markov process ,Service provider ,Reliability engineering ,symbols.namesake ,Server ,symbols ,Resource allocation ,Customer satisfaction ,Resource management ,Queue - Abstract
Manufactures and service provider institutes usually need queue theory to optimize their decisions about customers' waiting time. This will help them to specify resources that should be investigated and to provide customers' satisfaction. These two factors, resource allocation and customer satisfaction are so important for companies' survival essentially in a highly competitive environment. So describing queue systems performance in different environmental conditions is necessary. In this paper by analyzing actual queuing systems with layout constraints, a framework is introduced for specific conditions by using Markov chain concepts. This model can be a base for evaluating exponential queue systems with probability parameters. In this paper by providing a case study, it is tried to describe the proposed model. To do this, filling stations are analyzed in Tehran city.
- Published
- 2009
42. Formulating a robust strategy using scenario programming with a fuzzy logic approach
- Author
-
N. Vartanyans, Reza Radfar, and A.T. Eshlaghy
- Subjects
Strategic planning ,Engineering ,General method ,Operations research ,Robustness (computer science) ,Fuzzy inference system ,business.industry ,Management science ,Common method ,Scenario planning ,business ,Competitive advantage ,Fuzzy logic - Abstract
Future is less predictable, but the remarkable point is that organizations can prepare themselves to encounter it which will result in the creation of competitive advantage for them. In order to develop in the insecure environment, organizations should leave their unidimensional view toward the future, and consider the probable events in the future in their planning, using a multi-dimensional viewpoint. The methodology that is introduced in this article is a modern one because it combines the general method of formulating strategies with the two common tools that are used in order to fight uncertainty, namely, scenario planning and fuzzy logic. Using the uncertain elements that exist in the environment, this method embarks on designing possible scenarios facing the organization, and with the help of the fuzzy information supplied by the experts, it sets to select the most robust strategy of the organization in the fuzzy inference system. This strategy is selected in such a way that under all possible conditions of the occurrence of scenarios, it is justifiable and not necessarily the optimal choice; and enjoys the best possible performance from among all the scenarios that are specified for the future. In this paper, we compare the common method of strategy formulation with the formulation of strategy through the robust methodology, then, we examine the results obtained from implementation of both methods in a case study in a real organization.
- Published
- 2008
43. Long-Term Gain Estimation in Model-Based Single Channel Speech Separation
- Author
-
M.H. Radfar and Richard M. Dansereau
- Subjects
Engineering ,business.industry ,Acoustical engineering ,Speech recognition ,Frequency domain ,Range (statistics) ,Probability density function ,Speech processing ,business ,Energy (signal processing) ,Term (time) ,Communication channel - Abstract
Model-based single channel speech separation techniques commonly use trained patterns of the individual speakers to separate the speech signals. In most recent proposed techniques, it is assumed that data used in the train and test phase have the same level of energy, a prerequisite which is hardly met in the real situations. Considering this limitation, we propose a technique which estimates the gain associated with the individual speakers from the mixture and thus obviate the need for this assumption. The basic idea is to express the probability density function (PDF) of the mixture in terms of the individual speakers' PDFs and corresponding gains. Then, those patterns and gains which maximize the mixture's PDF are selected and used to recover the speech signals. Experimental results conducted on a wide variety of mixtures with signal-to-signal ratios ranging from 0 to 18 dB show that the proposed technique estimates the speakers' gain with 95% accuracy within the range of the actual gain ±%20. Comparing the separated speech signals with the original ones in terms of SNR criterion with/without including the gain estimation stage, we observe a significant SNR improvement (on average 5.73 dB) for the gain included scenario.
- Published
- 2007
44. Single Channel Speech Separation using Minimum Mean Square Error Estimation of Sources' Log Spectra
- Author
-
M.H. Radfar and Richard M. Dansereau
- Subjects
Minimum mean square error ,Channel (digital image) ,business.industry ,Gaussian ,Binary number ,Estimator ,Pattern recognition ,Speech processing ,Set (abstract data type) ,symbols.namesake ,symbols ,Artificial intelligence ,business ,Gaussian process ,Algorithm ,Mathematics - Abstract
We present an approach for separating two speech signals when only one single recording of their linear mixture is available. The log spectra of the sources are estimated from the mixture's log spectrum using minimum mean square error (MMSE) approach. The estimation is obtained from the assumption that the sources are modelled using a set of Gaussian subsources which are related to the mixture using MIXMAX approximation. The resulting estimator has a closed form and is expressed using the mean and variance of Gaussian subsources. In order to obtain the two most likely subsources which generate the mixture, we use the estimation-detection technique. We also show that the binary mask filtering which has been empirically - and with no mathematical justification - used in speech separation techniques is, in fact, a simplified form of the MMSE estimator. The proposed technique is compared with the binary mask when the input consists of male-male, female-female, and female-male mixtures. The experimental results in terms of segmental SNR show that the MMSE estimator outperforms binary mask filtering.
- Published
- 2007
45. A Joint Probabilistic-Deterministic Approach using Source-Filter Modeling of Speech Signal for Single Channel Speech Separation
- Author
-
Richard M. Dansereau, Abolghasem Sayadiyan, and M.H. Radfar
- Subjects
Computer Science::Sound ,Computer science ,Signal reconstruction ,Speech recognition ,Source separation ,Probability density function ,Filter (signal processing) ,Linear predictive coding ,Speech processing ,Signal ,Vocal tract - Abstract
In this paper, we present a new technique for separating two speech signals from a single recording. For this purpose, we decompose the speech signal into the excitation signal and the vocal tract function and then estimate the components from the mixed speech using a hybrid model. We first express the probability density function (PDF) of the mixed speech's log spectral vectors in terms of the PDFs of the underlying speech signal's vocal tract functions. Then, the mean vectors of PDFs of the vocal tract functions are obtained using a Maximum Likelihood estimator given the mixed signal. Finally, the estimated vocal tract function along with the extracted pitch values are used to reconstruct estimates of the individual speech signals. We compare our model with both an underdetermined blind source separation and a CASA method. The experimental results show our model outperforms both techniques in terms of SNR improvement and the percentage of crosstalk suppression.
- Published
- 2006
46. A Joint Identification-Separation Technique for Single Channel Speech Separation
- Author
-
Abolghasem Sayadiyan, Richard M. Dansereau, and M.H. Radfar
- Subjects
Voice activity detection ,Channel (digital image) ,Computer science ,business.industry ,Speech recognition ,Speech coding ,Pattern recognition ,Speech processing ,Linear predictive coding ,Identification (information) ,Source separation ,A priori and a posteriori ,Artificial intelligence ,business - Abstract
We present a generalized approach to speaker dependent model-based single channel speech separation techniques in which a priori knowledge of the underlying speakers is used to separate speech signals. For this purpose, we add an identification stage by which we first identify the underlying speakers in the mixture and then use the identified speakers' model to separate speech signals. The proposed technique not only preserves the advantages of model-based speaker dependent single channel speech separation algorithms (i.e. high separability) but also is able to separate the speech signals of an unlimited number of speakers given the speakers' models (i.e. generality). Evaluation results conducted on a database consisting of 100 mixed speech signals with target-to-interference ratios (TIR) ranging ?9 dB to +9 dB show significant performance improvements over those techniques which use a single model for all speakers.
- Published
- 2006
47. A Novel Low Complexity VQ-Based Single Channel Speech Separation Technique
- Author
-
Abolghasem Sayadiyan, Richard M. Dansereau, and M.H. Radfar
- Subjects
Fusion ,Channel (digital image) ,business.industry ,Feature vector ,Speech recognition ,Separation (statistics) ,Speech coding ,Vector quantization ,Pattern recognition ,Feature (computer vision) ,Lapped transform ,Artificial intelligence ,business ,Mathematics - Abstract
In this paper, a new single channel speech separation technique based on vector quantization (VQ) and the MIXMAX approximation is presented. At the core of this approach are two trained codebooks of the quantized feature vectors of speakers, whereby the main evaluation for separation is performed. The performance of the VQ-based approach is evaluated by applying three separate features: log spectrum, modulated lapped transform (MLT) coefficients, and a fusion of pitch and envelop information. The experiments are conducted in two different scenarios: speaker-dependent and speaker independent. The results show that the log spectrum outperforms the other features for speaker-dependent scenario. However, for the speaker independent scenario, the best results are obtained from applying the pitch-envelop feature.
- Published
- 2006
48. A New Approach for Classification of Weighting Methods
- Author
-
Abbas Toloie Eshlaghy and Reza Radfar
- Subjects
Weighted sum model ,Decision engineering ,business.industry ,Computer science ,Weighted product model ,Evidential reasoning approach ,computer.software_genre ,Machine learning ,Weighting ,Decision matrix ,Data mining ,Artificial intelligence ,business ,computer ,Decision analysis ,Optimal decision - Abstract
Preprocessing steps in MADM are very important and have a critical role in ranking operations. In many ranking algorithms, before running the models, it is necessary to do some modifications. These modifications are for example, Quantification, determination of utility of criteria, dimensionless operations for attributes, weighting methods and so on. Weighting methods try to define an importance of criteria in decision making process. Changing the weight in decision making process has a great influence in ranking results. Sometimes, determination of criteria weights are so difficult with conjoint of errors. There are many methods for this operation, but in literature we can not see an integrated model for classification of these methods. Methods such as entropy, LINMAP, eigenvector, smart, swing and so on, are the main weighting methods in this area. In this paper, our viewpoint for classification is multidimensional. To be or not to be decision making matrix, decision maker role in criteria weighting, number of criterion in weighting operation, and something like that. What is the weight for this criterion in decision making process? To answer, we must try to mine data from two different resources, first considering construction and layout of data in decision making matrix and second from opinion and perception of decision maker. We can see two main problems, first lack off the role of decision maker to finding weights by use decision making matrix and second educe of data from decision maker's opinion without attention to reliability and validity of data is very difficult. This paper tries to introduce a new approach for classification of current weighting methods and make a logical construction for this purpose. At the end, a new combinatorial model for reduce error and produce reliable and valid data for decision making is presented
- Published
- 2006
49. Study and Assessment of Technology Transfer Methods to Private Institutes and Companies
- Author
-
H Madani, H. Karimzadegan, and Reza Radfar
- Subjects
Engineering ,business.industry ,media_common.quotation_subject ,Conformity ,Technology management ,Engineering management ,Promotion (rank) ,Cultural diversity ,Scale (social sciences) ,Technology transfer ,Production (economics) ,business ,Adaptation (computer science) ,media_common - Abstract
The two main questions in this research are: 1) which biotechnology transfer methods relating to biotechnology have been used by the public institutes and private companies in Iran? and 2) how much successful were these methods? Regarding the importance of the issue, the method of implementing the research is based on the explanation and measurement. In this research the statistical community includes all the biotechnology projects in the commercial production scale. The research findings indicated that the most of the projects have chosen the modern technology transfer methods and processes, but their conformity, absorption, application, development, and promotion were respectively incomplete and imperfect. This finding differs from the complete technology transfer which could be successful. Perfect success of technology transfer in general and biotechnology in particular, is achieved when it leads to a complete transfer of the imported technology. Therefore, regarding the research findings and the comprehensive definition of biotechnology transfer, it is concluded that the success level of biotechnology transfer (based on the applied technology transfer methods) in the statistical community is incomplete.
- Published
- 2006
50. On the Choice of Window Size in Model-Based Single Channel Speech Separation
- Author
-
M.H. Radfar, Richard M. Dansereau, and Abolghasem Sayadiyan
- Subjects
Channel (digital image) ,Computer science ,Speech recognition ,Speech coding ,Separation (aeronautics) ,Vector quantization ,Process (computing) ,Window (computing) ,Speech processing ,Hamming code - Abstract
In this paper, we study the effect of window size on the performance of model-based single channel speech separation techniques. The separation system consists of two trained codebooks of the log spectral vectors of each speaker where by the main process of separation is performed. Four Hamming windows with the durations of 20, 32, 64, and 128 msec are used for short-time processing of the data. The experimental results show, in contrast with other speech processing applications, that a longer window must be applied for the separation purpose. Improvements in SNR of 2-3 dB are reported by using an optimal window selection which can significantly improve the performance of current model-based speech separation techniques.
- Published
- 2006
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.