Search

ThisSpecial Issue presents the latest advances in research and novel applications of speech and language technologies based on the works presented at the sixth edition of the IberSPEECH conference held in Granada in 2022, paying special attention to those focused on Iberian languages. IberSPEECH is the international conference of the Special Interest Group on Iberian Languages (SIG-IL) of the International Speech Communication Association (ISCA) and the Spanish Thematic Network on Speech Technologies (Red Temática en Tecnologías del Habla, or RTTH for short). Several researchers were invited to extend the contributions presented at IberSPEECH2022 due to their interest and quality. As a result, the Special Issue is composed of 11 papers that cover different research topics related to speech perception, speech analysis and enhancement, speaker verification and identification, speech production and synthesis, natural language processing, together with several applications and evaluation challenges.

Current articulatory-based three-dimensional source–filter models, which allow the production of vowels and diphtongs, still present very limited expressiveness. Glottal inverse filtering (GIF) techniques can become instrumental to identify specific characteristics of both the glottal source signal and the vocal tract transfer function to resemble expressive speech. Several GIF methods have been proposed in the literature; however, their comparison becomes difficult due to the lack of common and exhaustive experimental settings. In this work, first, a two-phase analysis methodology for the comparison of GIF techniques based on a reference dataset is introduced. Next, state-of-the-art GIF techniques based on iterative adaptive inverse filtering (IAIF) and quasi closed phase (QCP) approaches are thoroughly evaluated on OPENGLOT, an open database specifically designed to evaluate GIF, computing well-established GIF error measures after extending male vowels with their female counterparts. The results show that GIF methods obtain better results on male vowels. The QCP-based techniques significantly outperform IAIF-based methods for almost all error metrics and scenarios and are, at the same time, more stable across sex, phonation type, F0, and vowels. The IAIF variants improve the original technique for most error metrics on male vowels, while QCP with spectral tilt compensation achieves a lower spectral tilt error for male vowels than the original QCP.

Abstract Text-to-speech (TTS) synthesis systems have been widely used in general-purpose applications based on the generation of speech. Nonetheless, there are some domains, such as storytelling or voice output aid devices, which may also require singing. To enable a corpus-based TTS system to sing, a supplementary singing database should be recorded. This solution, however, might be too costly for eventual singing needs, or even unfeasible if the original speaker is unavailable or unable to sing properly. This work introduces a unit selection-based text-to-speech-and-singing (US-TTS&S) synthesis framework, which integrates speech-to-singing (STS) conversion to enable the generation of both speech and singing from an input text and a score, respectively, using the same neutral speech corpus. The viability of the proposal is evaluated considering three vocal ranges and two tempos on a proof-of-concept implementation using a 2.6-h Spanish neutral speech corpus. The experiments show that challenging STS transformation factors are required to sing beyond the corpus vocal range and/or with notes longer than 150 ms. While score-driven US configurations allow the reduction of pitch-scale factors, time-scale factors are not reduced due to the short length of the spoken vowels. Moreover, in the MUSHRA test, text-driven and score-driven US configurations obtain similar naturalness rates of around 40 for all the analysed scenarios. Although these naturalness scores are far from those of vocaloid, the singing scores of around 60 which were obtained validate that the framework could reasonably address eventual singing needs.

The source-filter model is one of the main techniques applied to speech analysis and synthesis. Recent advances in voice production by means of three-dimensional (3D) source-filter models have overcome several limitations of classic one-dimensional techniques. Despite the development of preliminary attempts to improve the expressiveness of 3D-generated voices, they are still far from achieving realistic results. Towards this goal, this work analyses the contribution of both the the vocal tract (VT) and the glottal source spectral (GSS) cues in the generation of happy and aggressive speech through a GlottDNN-based analysis-by-synthesis methodology. Paired neutral expressive utterances are parameterised to generate different combinations of expressive vowels, applying the target expressive GSS and/or VT cues on the neutral vowels after transplanting the expressive prosody on these utterances. The conducted objective tests focused on Spanish [a], [i] and [u] vowels show that both GSS and VT cues significantly reduce the spectral distance to the expressive target. The results from the perceptual test show that VT cues make a statistically significant contribution in the expression of happy and aggressive emotions for [a] vowels, while the GSS contribution is significant in [i] and [u] vowels.

Environmental noise has become one of the principal health risks for urban dwellers and road traffic noise (RTN) is considered to be the main source of these adverse effects. To address this problem, strategic noise maps and corresponding action plans have been developed throughout Europe in recent years in response to the European Noise Directive 2002/49/EC (END), especially in populated cities. Recently, wireless acoustic sensor networks (WASNs) have started to serve as an alternative to static noise maps to monitor urban areas by gathering environmental noise data in real time. Several studies have analysed and categorized the different acoustic environments described in the END (e.g., traffic, industrial, leisure, etc.). However, most of them have only considered the dynamic evolution of the A-weighted equivalent noise levels LAeq over different periods of time. In order to focus on the analysis of RTN solely, this paper introduces a clustering methodology to analyse and group spectro-temporal profiles of RTN collected simultaneously across an area of interest. The experiments were conducted on two acoustic databases collected during a weekday and a weekend day through WASNs deployed in the pilot areas of the LIFE+ DYNAMAP project. The results obtained show that the clustering of RTN, based on its spectro-temporal patterns, yields different solutions on weekdays and at weekends in both environments, being larger than those found in the suburban environment and lower than the number of clusters in the urban scenario.

In addition to air pollution, environmental noise has become one of the major hazards for citizens, being Road Traffic Noise (RTN) as its main source in urban areas. Recently, low-cost Wireless Acoustic Sensor Networks (WASNs) have become an alternative to traditional strategic noise mapping in cities. In order to monitor RTN solely, WASN-based approaches should automatize the off-line removal of those events unrelated to regular road traffic (e.g., sirens, airplanes, trams, etc.). Within the LIFE DYNAMAP project, 15 urban Anomalous Noise Events (ANEs) were described through an expert-based recording campaign. However, that work only focused on the overall analysis of the events gathered during non-sequential diurnal periods. As a step forward to characterize the temporal and local particularities of urban ANEs in real acoustic environments, this work analyses their distribution between day (06:00–22:00) and night (22:00–06:00) in narrow (1 lane) and wide (more than 1 lane) streets. The study is developed on a manually-labelled 151-h acoustic database obtained from the 24-nodes WASN deployed across DYNAMAP’s Milan pilot area during a weekday and a weekend day. Results confirm the unbalanced nature of the problem (RTN represents 83.5% of the data), while identifying 26 ANE subcategories mainly derived from pedestrians, animals, transports and industry. Their presence depends more significantly on the time period than on the street type, as most events have been observed in the day-time during the weekday, despite being especially present in narrow streets. Moreover, although ANEs show quite similar median durations regardless of time and location in general terms, they usually present higher median signal-to-noise ratios at night, mainly on the weekend, which becomes especially relevant for the WASN-based computation of equivalent RTN levels.

Road Traffic Noise (RTN) is one of the main pollutants in urban and suburban areas, negatively affecting the quality of life of their inhabitants. In the context of the European LIFE DYNAMAP project, two Wireless Acoustic Sensor Networks (WASN) have been deployed to monitor RTN: one in District 9 of Milan, and another along the A90 motorway of Rome. Since the dynamic mapping system should be able to identify and remove those Anomalous Noise Events (ANEs) unrelated to regular road traffic (e.g., sirens, horns, speech, and doors), an Anomalous Noise Event Detector (ANED) has been included in the dynamic noise mapping pipeline to avoid biasing the computation of the equivalent RTN levels. After deploying the 24 low-cost acoustic sensor networks in both pilot areas, WASN-based acoustic datasets were built to adapt the previous version of the ANED algorithm to run in real-operation conditions. In this work, we describe the preliminary results of the analysis of the 154 h WASN-based urban acoustic dataset obtained from the Milan city in terms of the main characteristics of ANEs. The results confirm the unbalanced nature of the problem (83.7% of the data corresponds to RTN), showing the urban WASN-based dataset a larger number of ANEs with higher local predominance than what was observed in the previous expert-based recording campaign, which underlines the importance of the accurate modeling of the urban acoustic environment to train the ANED properly.

The main goal of this Special Issue is to present the latest advances in research and novel applications of speech and language technologies based on the works presented at the IberSPEECH edition held in Barcelona in 2018, paying special attention to those focused on Iberian languages. IberSPEECH is the international conference of the Special Interest Group on Iberian Languages (SIG-IL) of the International Speech Communication Association (ISCA) and of the Spanish Thematic Network on Speech Technologies (Red Temática en Tecnologías del Habla, or RTTH for short). Several researchers were invited to extend their contributions presented at IberSPEECH2018 due to their interest and quality. As a result, this Special Issue is composed of 13 papers that cover different topics of investigation related to perception, speech analysis and enhancement, speaker verification and identification, speech production and synthesis, natural language processing, together with several applications and evaluation challenges.

Environmental noise can be defined as the accumulation of noise pollution caused by sounds generated by outdoor human activities, Road Traffic Noise (RTN) being the main source in urban and suburban areas. To address the negative effects of environmental noise on public health, the European Environmental Noise Directive requires EU member states to tailor noise maps and define the corresponding action plans every five years for major agglomerations and key infrastructures. Noise maps have been hitherto created from expert-based measurements, after cleaning the recorded acoustic data of undesired acoustic events, or Anomalous Noise Events (ANEs). In recent years, Wireless Acoustic Sensor Networks (WASNs) have become an alternative. However, most of the proposals focus on measuring global noise levels without taking into account the presence of ANEs. The LIFE DYNAMAP project has developed a WASN-based dynamic noise mapping system to analyze the acoustic impact of road infrastructures in real time based solely on RTN levels. After studying the bias caused by individual ANEs on the computation of the A-weighted equivalent noise levels through an expert-based dataset obtained before installing the sensor networks, this work evaluates the aggregate impact of the ANEs on the RTN measurements in a real-operation environment. To that effect, 304 h and 20 min of labeled acoustic data collected through the two WASNs deployed in both pilot areas have been analyzed, computing the individual and aggregate impacts of ANEs for each sensor location and impact range (low, medium and high) for a 5 min integration time. The study shows the regular occurrence of ANEs when monitoring RTN levels in both acoustic environments, which are especially common in the urban area. Moreover, the results reveal that the aggregate contribution of low- and medium-impact ANEs can become as critical as the presence of high-impact individual ANEs, thus highlighting the importance of their automatic removal to obtain reliable WASN-based RTN maps in real-operation environments.

Articulatory speech synthesis has long been based on one-dimensional (1D) approaches. They assume plane wave propagation within the vocal tract and disregard higher order modes that typically appear above 5 kHz. However, such modes may be relevant in obtaining a more natural voice, especially for phonation types with significant high frequency energy (HFE) content. This work studies the contribution of the glottal source at high frequencies in the 3D numerical synthesis of vowels. The spoken vocal range is explored using an LF (Liljencrants–Fant) model enhanced with aspiration noise and controlled by the R d glottal shape parameter. The vowels [ɑ], [i], and [u] are generated with a finite element method (FEM) using realistic 3D vocal tract geometries obtained from magnetic resonance imaging (MRI), as well as simplified straight vocal tracts of a circular cross-sectional area. The symmetry of the latter prevents the onset of higher order modes. Thus, the comparison between realistic and simplified geometries enables us to analyse the influence of such modes. The simulations indicate that higher order modes may be perceptually relevant, particularly for tense phonations (lower R d values) and/or high fundamental frequency values, F 0 s. Conversely, vowels with a lax phonation and/or low F0s may result in inaudible HFE levels, especially if aspiration noise is not considered in the glottal source model.

Traffic noise is presently considered one of the main pollutants in urban and suburban areas. Several recent technological advances have allowed a step forward in the dynamic computation of road-traffic noise levels by means of a Wireless Acoustic Sensor Network (WASN) through the collection of measurements in real-operation environments. In the framework of the LIFE DYNAMAP project, two WASNs have been deployed in two pilot areas: one in the city of Milan, as an urban environment, and another around the city of Rome in a suburban location. For a correct evaluation of the noise level generated by road infrastructures, all Anomalous Noise Events (ANE) unrelated to regular road-traffic noise (e.g., sirens, horns, speech, etc.) should be removed before updating corresponding noise maps. This work presents the production and analysis of a real-operation environmental audio database collected through the 19-node WASN of a suburban area. A total of 156 h and 20 min of labeled audio data has been obtained differentiating among road-traffic noise and ANEs (classified in 16 subcategories). After delimiting their boundaries manually, the acoustic salience of the ANE samples is automatically computed as a contextual Signal-to-Noise Ratio (SNR) together with its impact on the A-weighted equivalent level ( Δ L A e q ). The analysis of the real-operation WASN-based environmental database is evaluated with these metrics, and we conclude that the 19 locations of the network present substantial differences in the occurrences of the subcategories of ANE, with a clear predominance of the noise of sirens, trains, and thunder.

City noise and sound are measured and processed with the purpose of drawing appropriate government legislation and regulations, ultimately aimed at contributing to a healthier environment for humans. The primary use of urban noise analysis is carried out with the main purpose of reporting or denouncing, to the appropriate authorities, a misconduct or correct a misuse of council resources. We believe that urban sounds carry more information than what it is extracted to date. In this paper we present a cloud-based urban sound analysis system for the capturing, processing and trading of urban sound-based information. By leveraging modern artificial intelligence algorithms running on a FOG computing city infrastructure, we will show how the presented solution can offer a valuable solution for exploiting urban sound information. A specific focus is given to the hardware implementation of the sound sensor and its multimicrophone architecture. We discuss how the presented architecture is designed to allow the trading of sound information between independent parties, transparently, using cloud-based sound processing APIs running on an inexpensive consumer-grade microphone.

The DYNAMAP project is aimed at implementing a dynamic noise mapping system able to determine the acoustic impact of road infrastructures in real time. It was established as a result of the European Noise Directive 2002/49/EC. A Wireless Acoustic Sensor Network (WASN) is used to collect the measurements in two pilot areas: in the city of Milan (urban) and on the A90 motorway around Rome (suburban). For a proper evaluation of the noise level of the road infrastructures, the anomalous noise events (ANE) unrelated to traffic noise (e.g., sirens, horns, speech, doors, etc.) should be removed before updating the noise maps. For this purpose, an anomalous noise events detector (ANED) was initially designed and trained using data from a real-life recording campaign. In this work, we continue adapting the ANED algorithm to conform to the requirements of the final 25-node hybrid WASN deployed in the suburban environment. Specifically, the study focuses on the analysis of the spectro-temporal characteristics of the acoustic data in real-operation conditions and their differences between the 19 high-capacity nodes in the Rome pilot area in order to adapt the ANED to run on the entire WASN appropriately.

One of the main aspects affecting the quality of life of people living in urban and suburban areas is the continuous exposure to high road traffic noise (RTN) levels. Nowadays, thanks to Wireless Acoustic Sensor Networks (WASN) noise in Smart Cities has started to be automatically mapped. To obtain a reliable picture of the RTN, those anomalous noise events (ANE) unrelated to road traffic (sirens, horns, people, etc.) should be removed from the noise map computation by means of an Anomalous Noise Event Detector (ANED). In Hybrid WASNs, with master-slave architecture, ANED should be implemented in both high-capacity (Hi-Cap) and low-capacity (Lo-Cap) sensors, following the same principle to obtain consistent results. This work presents an ANED version to run in real-time on μ Controller-based Lo-Cap sensors of a hybrid WASN, discriminating RTN from ANE through their Mel-based spectral energy differences. The experiments, considering 9 h and 8 min of real-life acoustic data from both urban and suburban environments, show the feasibility of the proposal both in terms of computational load and in classification accuracy. Specifically, the ANED Lo-Cap requires around 1 6 of the computational load of the ANED Hi-Cap, while classification accuracies are slightly lower (around 10%). However, preliminary analyses show that these results could be improved in around 4% in the future by means of considering optimal frequency selection.

One of the main aspects affecting the quality of life of people living in urban and suburban areas is their continued exposure to high Road Traffic Noise (RTN) levels. Until now, noise measurements in cities have been performed by professionals, recording data in certain locations to build a noise map afterwards. However, the deployment of Wireless Acoustic Sensor Networks (WASN) has enabled automatic noise mapping in smart cities. In order to obtain a reliable picture of the RTN levels affecting citizens, Anomalous Noise Events (ANE) unrelated to road traffic should be removed from the noise map computation. To this aim, this paper introduces an Anomalous Noise Event Detector (ANED) designed to differentiate between RTN and ANE in real time within a predefined interval running on the distributed low-cost acoustic sensors of a WASN. The proposed ANED follows a two-class audio event detection and classification approach, instead of multi-class or one-class classification schemes, taking advantage of the collection of representative acoustic data in real-life environments. The experiments conducted within the DYNAMAP project, implemented on ARM-based acoustic sensors, show the feasibility of the proposal both in terms of computational cost and classification performance using standard Mel cepstral coefficients and Gaussian Mixture Models (GMM). The two-class GMM core classifier relatively improves the baseline universal GMM one-class classifier F1 measure by 18.7% and 31.8% for suburban and urban environments, respectively, within the 1-s integration interval. Nevertheless, according to the results, the classification performance of the current ANED implementation still has room for improvement.

Fast environmental variations due to climate change can cause mass decline or even extinctions of species, having a dramatic impact on the future of biodiversity. During the last decade, different approaches have been proposed to track and monitor endangered species, generally based on costly semi-automatic systems that require human supervision adding limitations in coverage and time. However, the recent emergence of Wireless Acoustic Sensor Networks (WASN) has allowed non-intrusive remote monitoring of endangered species in real time through the automatic identification of the sound they emit. In this work, an FPGA-based WASN centralized architecture is proposed and validated on a simulated operation environment. The feasibility of the architecture is evaluated in a case study designed to detect the threatened Botaurus stellaris among other 19 cohabiting birds species in The Parc Natural dels Aiguamolls de l’Empord

Traffic noise is one of the main pollutants in urban and suburban areas. European authorities have driven several initiatives to study, prevent and reduce the effects of exposure of population to traffic. Recent technological advances have allowed the dynamic computation of noise levels by means of Wireless Acoustic Sensor Networks (WASN) such as that developed within the European LIFE DYNAMAP project. Those WASN should be capable of detecting and discarding non-desired sound sources from road traffic noise, denoted as anomalous noise events (ANE), in order to generate reliable noise level maps. Due to the local, occasional and diverse nature of ANE, some works have opted to artificially build ANE databases at the cost of misrepresentation. This work presents the production and analysis of a real-life environmental audio database in two urban and suburban areas specifically conceived for anomalous noise events’ collection. A total of 9 h 8 min of labelled audio data is obtained differentiating among road traffic noise, background city noise and ANE. After delimiting their boundaries manually, the acoustic salience of the ANE samples is automatically computed as a contextual signal-to-noise ratio (SNR). The analysis of the real-life environmental database shows high diversity of ANEs in terms of occurrences, durations and SNRs, as well as confirming both the expected differences between the urban and suburban soundscapes in terms of occurrences and SNRs, and the rare nature of ANE.

One of the main priorities of smart cities is improving the quality of life of their inhabitants. Traffic noise is one of the pollutant sources that causes a negative impact on the quality of life of citizens, which is gaining attention among authorities. The European Commission has promoted the Environmental Noise Directive 2002/49/EC (END) to inform citizens and to prevent the harmful effects of noise exposure. The measure of acoustic levels using noise maps is a strategic issue in the END action plan. Noise maps are typically calculated by computing the average noise during one year and updated every five years. Hence, the implementation of dynamic noise mapping systems could lead to short-term plan actions, besides helping to better understand the evolution of noise levels along time. Recently, some projects have started the monitoring of noise levels in urban areas by means of acoustic sensor networks settled in strategic locations across the city, while others have taken advantage of collaborative citizen sensing mobile applications. In this paper, we describe the design of an acoustic low-cost sensor network installed on public buses to measure the traffic noise in the city in real time. Moreover, the challenges that a ubiquitous bus acoustic measurement system entails are enumerated and discussed. Specifically, the analysis takes into account the feature extraction of the audio signal, the identification and separation of the road traffic noise from urban traffic noise, the hardware platform to measure and process the acoustic signal, the connectivity between the several nodes of the acoustic sensor network to store the data and, finally, the noise maps’ generation process. The implementation and evaluation of the proposal in a real-life scenario is left for future work.

Endowing machines with sensing capabilities similar to those of humans is a prevalent quest in engineering and computer science. In the pursuit of making computers sense their surroundings, a huge effort has been conducted to allow machines and computers to acquire, process, analyze and understand their environment in a human-like way. Focusing on the sense of hearing, the ability of computers to sense their acoustic environment as humans do goes by the name of machine hearing. To achieve this ambitious aim, the representation of the audio signal is of paramount importance. In this paper, we present an up-to-date review of the most relevant audio feature extraction techniques developed to analyze the most usual audio signals: speech, music and environmental sounds. Besides revisiting classic approaches for completeness, we include the latest advances in the field based on new domains of analysis together with novel bio-inspired proposals. These approaches are described following a taxonomy that organizes them according to their physical or perceptual basis, being subsequently divided depending on the domain of computation (time, frequency, wavelet, image-based, cepstral, or other domains). The description of the approaches is accompanied with recent examples of their application to machine hearing related problems.