Search

Nowadays, open-source large language models like LLaMA have emerged. Recent developments have incorporated supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to align these models with human goals. However, SFT methods treat all training data with mixed quality equally, while RLFT methods require high-quality pairwise or ranking-based preference data. In this study, we present a novel framework, named OpenChat, to advance open-source language models with mixed-quality data. Specifically, we consider the general SFT training data, consisting of a small amount of expert data mixed with a large proportion of sub-optimal data, without any preference labels. We propose the C(onditioned)-RLFT, which regards different data sources as coarse-grained reward labels and learns a class-conditioned policy to leverage complementary data quality information. Interestingly, the optimal policy in C-RLFT can be easily solved through single-stage, RL-free supervised learning, which is lightweight and avoids costly human preference labeling. Through extensive experiments on three standard benchmarks, our openchat-13b fine-tuned with C-RLFT achieves the highest average performance among all 13b open-source language models. Moreover, we use AGIEval to validate the model generalization performance, in which only openchat-13b surpasses the base model. Finally, we conduct a series of analyses to shed light on the effectiveness and robustness of OpenChat. Our code, data, and models are publicly available at https://github.com/imoneoi/openchat and https://huggingface.co/openchat.

Recently, the instruction-tuning of large language models is a crucial area of research in the field of natural language processing. Due to resource and cost limitations, several researchers have employed parameter-efficient tuning techniques, such as LoRA, for instruction tuning, and have obtained encouraging results In comparison to full-parameter fine-tuning, LoRA-based tuning demonstrates salient benefits in terms of training costs. In this study, we undertook experimental comparisons between full-parameter fine-tuning and LoRA-based tuning methods, utilizing LLaMA as the base model. The experimental results show that the selection of the foundational model, training dataset scale, learnable parameter quantity, and model training cost are all important factors. We hope that the experimental conclusions of this paper can provide inspiration for training large language models, especially in the field of Chinese, and help researchers find a better trade-off strategy between training cost and model performance. To facilitate the reproduction of the paper's results, the dataset, model and code will be released.

Recently, significant public efforts have been directed towards developing low-cost models with capabilities akin to ChatGPT, thereby fostering the growth of open-source conversational models. However, there remains a scarcity of comprehensive and in-depth evaluations of these models' performance. In this study, we examine the influence of training data factors, including quantity, quality, and linguistic distribution, on model performance. Our analysis is grounded in several publicly accessible, high-quality instruction datasets, as well as our own Chinese multi-turn conversations. We assess various models using a evaluation set of 1,000 samples, encompassing nine real-world scenarios. Our goal is to supplement manual evaluations with quantitative analyses, offering valuable insights for the continued advancement of open-source chat models. Furthermore, to enhance the performance and training and inference efficiency of models in the Chinese domain, we extend the vocabulary of LLaMA - the model with the closest open-source performance to proprietary language models like GPT-3 - and conduct secondary pre-training on 3.4B Chinese words. We make our model, data, as well as code publicly available.

The success of ChatGPT has recently attracted numerous efforts to replicate it, with instruction-tuning strategies being a key factor in achieving remarkable results. Instruction-tuning not only significantly enhances the model's performance and generalization but also makes the model's generated results more consistent with human speech patterns. However current research rarely studies the impact of different amounts of instruction data on model performance, especially in the real-world use cases. In this paper we explore the performance of large language models based on instruction tuning across different scales of instruction data. An evaluation dataset consisting of 12 major online use cases is constructed in the experiment. With Bloomz-7B1-mt as the base model, the results show that 1) merely increasing the amount of instruction data leads to continuous improvement in tasks such as open-ended generation, 2) in tasks such as math and code, the model performance curve remains quite flat while increasing data size. We further analyze the possible causes of these phenomena and propose potential future research directions such as effectively selecting high-quality training data, scaling base models and training methods specialized for hard tasks. We will release our training and evaluation datasets, as well as model checkpoints.

As a natural language assistant, ChatGPT is capable of performing various tasks, including but not limited to article generation, code completion, and data analysis. Furthermore, ChatGPT has consistently demonstrated a remarkable level of accuracy and reliability in terms of content evaluation, exhibiting the capability of mimicking human preferences. To further explore ChatGPT's potential in this regard, a study is conducted to assess its ability to rank content. In order to do so, a test set consisting of prompts is created, covering a wide range of use cases, and five models are utilized to generate corresponding responses. ChatGPT is then instructed to rank the responses generated by these models. The results on the test set show that ChatGPT's ranking preferences are consistent with human to a certain extent. This preliminary experimental finding implies that ChatGPT's zero-shot ranking capability could be used to reduce annotation pressure in a number of ranking tasks.

In this paper, we delve into semi-supervised 2D human pose estimation. The previous method ignored two problems: (i) When conducting interactive training between large model and lightweight model, the pseudo label of lightweight model will be used to guide large models. (ii) The negative impact of noise pseudo labels on training. Moreover, the labels used for 2D human pose estimation are relatively complex: keypoint category and keypoint position. To solve the problems mentioned above, we propose a semi-supervised 2D human pose estimation framework driven by a position inconsistency pseudo label correction module (SSPCM). We introduce an additional auxiliary teacher and use the pseudo labels generated by the two teacher model in different periods to calculate the inconsistency score and remove outliers. Then, the two teacher models are updated through interactive training, and the student model is updated using the pseudo labels generated by two teachers. To further improve the performance of the student model, we use the semi-supervised Cut-Occlude based on pseudo keypoint perception to generate more hard and effective samples. In addition, we also proposed a new indoor overhead fisheye human keypoint dataset WEPDTOF-Pose. Extensive experiments demonstrate that our method outperforms the previous best semi-supervised 2D human pose estimation method. We will release the code and dataset at https://github.com/hlz0606/SSPCM.

PCL detection task is aimed at identifying and categorizing language that is patronizing or condescending towards vulnerable communities in the general media.Compared to other NLP tasks of paragraph classification, the negative language presented in the PCL detection task is usually more implicit and subtle to be recognized, making the performance of common text-classification approaches disappointed. Targeting the PCL detection problem in SemEval-2022 Task 4, in this paper, we give an introduction to our team's solution, which exploits the power of prompt-based learning on paragraph classification. We reformulate the task as an appropriate cloze prompt and use pre-trained Masked Language Models to fill the cloze slot. For the two subtasks, binary classification and multi-label classification, DeBERTa model is adopted and fine-tuned to predict masked label words of task-specific prompts. On the evaluation dataset, for binary classification, our approach achieves an F1-score of 0.6406; for multi-label classification, our approach achieves an macro-F1-score of 0.4689 and ranks first in the leaderboard.

Machine Reading Comprehension with Unanswerable Questions is a difficult NLP task, challenged by the questions which can not be answered from passages. It is observed that subtle literal changes often make an answerable question unanswerable, however, most MRC models fail to recognize such changes. To address this problem, in this paper, we propose a span-based method of Contrastive Learning (spanCL) which explicitly contrast answerable questions with their answerable and unanswerable counterparts at the answer span level. With spanCL, MRC models are forced to perceive crucial semantic changes from slight literal differences. Experiments on SQuAD 2.0 dataset show that spanCL can improve baselines significantly, yielding 0.86-2.14 absolute EM improvements. Additional experiments also show that spanCL is an effective way to utilize generated questions.

This paper describes our best system and methodology for ADD 2022: The First Audio Deep Synthesis Detection Challenge\cite{Yi2022ADD}. The very same system was used for both two rounds of evaluation in Track 3.2 with a similar training methodology. The first round of Track 3.2 data is generated from Text-to-Speech(TTS) or voice conversion (VC) algorithms, while the second round of data consists of generated fake audio from other participants in Track 3.1, aiming to spoof our systems. Our systems use a standard 34-layer ResNet, with multi-head attention pooling \cite{india2019self} to learn the discriminative embedding for fake audio and spoof detection. We further utilize neural stitching to boost the model's generalization capability in order to perform equally well in different tasks, and more details will be explained in the following sessions. The experiments show that our proposed method outperforms all other systems with a 10.1% equal error rate(EER) in Track 3.2., Comment: Accepted to ICASSP 2022

In this paper, we describe our speech generation system for the first Audio Deep Synthesis Detection Challenge (ADD 2022). Firstly, we build an any-to-many voice conversion (VC) system to convert source speech with arbitrary language content into the target speaker%u2019s fake speech. Then the converted speech generated from VC is post-processed in the time domain to improve the deception ability. The experimental results show that our system has adversarial ability against anti-spoofing detectors with a little compromise in audio quality and speaker similarity. This system ranks top in Track 3.1 in the ADD 2022, showing that our method could also gain good generalization ability against different detectors., Comment: Accepted to ICASSP 2022

This paper presents the details of our system designed for the Task 1 of Multimodal Information Based Speech Processing (MISP) Challenge 2021. The purpose of Task 1 is to leverage both audio and video information to improve the environmental robustness of far-field wake word spotting. In the proposed system, firstly, we take advantage of speech enhancement algorithms such as beamforming and weighted prediction error (WPE) to address the multi-microphone conversational audio. Secondly, several data augmentation techniques are applied to simulate a more realistic far-field scenario. For the video information, the provided region of interest (ROI) is used to obtain visual representation. Then the multi-layer CNN is proposed to learn audio and visual representations, and these representations are fed into our two-branch attention-based network which can be employed for fusion, such as transformer and conformed. The focal loss is used to fine-tune the model and improve the performance significantly. Finally, multiple trained models are integrated by casting vote to achieve our final 0.091 score., Comment: Accepted to ICASSP 2022

This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition training, and to filter out segments with low-quality transcription. For system training, GigaSpeech provides five subsets of different sizes, 10h, 250h, 1000h, 2500h, and 10000h. For our 10,000-hour XL training subset, we cap the word error rate at 4% during the filtering/validation stage, and for all our other smaller training subsets, we cap it at 0%. The DEV and TEST evaluation sets, on the other hand, are re-processed by professional human transcribers to ensure high transcription quality. Baseline systems are provided for popular speech recognition toolkits, namely Athena, ESPnet, Kaldi and Pika.

End-to-end models have gradually become the preferred option for automatic speech recognition (ASR) applications. During the training of end-to-end ASR, data augmentation is a quite effective technique for regularizing the neural networks. This paper proposes a novel data augmentation technique based on semantic transposition of the transcriptions via syntax rules for end-to-end Mandarin ASR. Specifically, we first segment the transcriptions based on part-of-speech tags. Then transposition strategies, such as placing the object in front of the subject or swapping the subject and the object, are applied on the segmented sentences. Finally, the acoustic features corresponding to the transposed transcription are reassembled based on the audio-to-text forced-alignment produced by a pre-trained ASR system. The combination of original data and augmented one is used for training a new ASR system. The experiments are conducted on the Transformer[2] and Conformer[3] based ASR. The results show that the proposed method can give consistent performance gain to the system. Augmentation related issues, such as comparison of different strategies and ratios for data combination are also investigated.

Speaker extraction aims to extract target speech signal from a multi-talker environment with interference speakers and surrounding noise, given the target speaker's reference information. Most speaker extraction systems achieve satisfactory performance on the premise that the test speakers have been encountered during training time. Such systems suffer from performance degradation given unseen target speakers and/or mismatched reference voiceprint information. In this paper we propose a novel strategy named Iterative Refined Adaptation (IRA) to improve the robustness and generalization capability of speaker extraction systems in the aforementioned scenarios. Given an initial speaker embedding encoded by an auxiliary network, the extraction network can obtain a latent representation of the target speaker, which is fed back to the auxiliary network to get a refined embedding to provide more accurate guidance for the extraction network. Experiments on WSJ0-2mix-extr and WHAM! dataset confirm the superior performance of the proposed method over the network without IRA in terms of SI-SDR and PESQ improvement., Comment: Accepted by Interspeech 2021

Self-supervised visual pretraining has shown significant progress recently. Among those methods, SimCLR greatly advanced the state of the art in self-supervised and semi-supervised learning on ImageNet. The input feature representations for speech and visual tasks are both continuous, so it is natural to consider applying similar objective on speech representation learning. In this paper, we propose Speech SimCLR, a new self-supervised objective for speech representation learning. During training, Speech SimCLR applies augmentation on raw speech and its spectrogram. Its objective is the combination of contrastive loss that maximizes agreement between differently augmented samples in the latent space and reconstruction loss of input representation. The proposed method achieved competitive results on speech emotion recognition and speech recognition.

Audio Visual Scene-aware Dialog (AVSD) is a task to generate responses when discussing about a given video. The previous state-of-the-art model shows superior performance for this task using Transformer-based architecture. However, there remain some limitations in learning better representation of modalities. Inspired by Neural Machine Translation (NMT), we propose the Transformer-based Modal Translator (TMT) to learn the representations of the source modal sequence by translating the source modal sequence to the related target modal sequence in a supervised manner. Based on Multimodal Transformer Networks (MTN), we apply TMT to video and dialog, proposing MTN-TMT for the video-grounded dialog system. On the AVSD track of the Dialog System Technology Challenge 7, MTN-TMT outperforms the MTN and other submission models in both Video and Text task and Text Only task. Compared with MTN, MTN-TMT improves all metrics, especially, achieving relative improvement up to 14.1% on CIDEr. Index Terms: multimodal learning, audio-visual scene-aware dialog, neural machine translation, multi-task learning

This paper introduces a new open-sourced Mandarin speech corpus, called DiDiSpeech. It consists of about 800 hours of speech data at 48kHz sampling rate from 6000 speakers and the corresponding texts. All speech data in the corpus is recorded in quiet environment and is suitable for various speech processing tasks, such as voice conversion, multi-speaker text-to-speech and automatic speech recognition. We conduct experiments with multiple speech tasks and evaluate the performance, showing that it is promising to use the corpus for both academic research and practical application. The corpus is available at https://outreach.didichuxing.com/research/opendata/., Comment: 5 pages, 2 figures, 11 tables

This paper describes DiDi AI Labs' submission to the WMT2020 news translation shared task. We participate in the translation direction of Chinese->English. In this direction, we use the Transformer as our baseline model, and integrate several techniques for model enhancement, including data filtering, data selection, back-translation, fine-tuning, model ensembling, and re-ranking. As a result, our submission achieves a BLEU score of $36.6$ in Chinese->English., Comment: Accepted at WMT 2020

Recent work has shown that it is feasible to use generative adversarial networks (GANs) for speech enhancement, however, these approaches have not been compared to state-of-the-art (SOTA) non GAN-based approaches. Additionally, many loss functions have been proposed for GAN-based approaches, but they have not been adequately compared. In this study, we propose novel convolutional recurrent GAN (CRGAN) architectures for speech enhancement. Multiple loss functions are adopted to enable direct comparisons to other GAN-based systems. The benefits of including recurrent layers are also explored. Our results show that the proposed CRGAN model outperforms the SOTA GAN-based models using the same loss functions and it outperforms other non-GAN based systems, indicating the benefits of using a GAN for speech enhancement. Overall, the CRGAN model that combines an objective metric loss function with the mean squared error (MSE) provides the best performance over comparison approaches across many evaluation metrics., Comment: accepted by Interspeech2020, 5 pages, 2 figures

Recently, a variety of acoustic tasks and related applications arised. For many acoustic tasks, the labeled data size may be limited. To handle this problem, we propose an unsupervised pre-training method using Transformer based encoder to learn a general and robust high-level representation for all acoustic tasks. Experiments have been conducted on three kinds of acoustic tasks: speech emotion recognition, sound event detection and speech translation. All the experiments have shown that pre-training using its own training data can significantly improve the performance. With a larger pre-training data combining MuST-C, Librispeech and ESC-US datasets, for speech emotion recognition, the UAR can further improve absolutely 4.3% on IEMOCAP dataset. For sound event detection, the F1 score can further improve absolutely 1.5% on DCASE2018 task5 development set and 2.1% on evaluation set. For speech translation, the BLEU score can further improve relatively 12.2% on En-De dataset and 8.4% on En-Fr dataset., Comment: Accepted by ICASSP 2021

Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many unsupervised pre-training methods have been proposed. Among these methods, Masked Predictive Coding achieved significant improvements on various speech recognition datasets with BERT-like Masked Reconstruction loss and Transformer backbone. However, many aspects of MPC have not been fully investigated. In this paper, we conduct a further study on MPC and focus on three important aspects: the effect of pre-training data speaking style, its extension on streaming model, and how to better transfer learned knowledge from pre-training stage to downstream tasks. Experiments reveled that pre-training data with matching speaking style is more useful on downstream recognition tasks. A unified training objective with APC and MPC provided 8.46% relative error reduction on streaming model trained on HKUST. Also, the combination of target data adaption and layer-wise discriminative training helped the knowledge transfer of MPC, which achieved 3.99% relative error reduction on AISHELL over a strong baseline.

Multi-class text classification is one of the key problems in machine learning and natural language processing. Emerging neural networks deal with the problem using a multi-output softmax layer and achieve substantial progress, but they do not explicitly learn the correlation among classes. In this paper, we use a multi-task framework to address multi-class classification, where a multi-class classifier and multiple binary classifiers are trained together. Moreover, we employ adversarial training to distinguish the class-specific features and the class-agnostic features. The model benefits from better feature representation. We conduct experiments on two large-scale multi-class text classification tasks and demonstrate that the proposed architecture outperforms baseline approaches.

Text summarization aims to generate a headline or a short summary consisting of the major information of the source text. Recent studies employ the sequence-to-sequence framework to encode the input with a neural network and generate abstractive summary. However, most studies feed the encoder with the semantic word embedding but ignore the syntactic information of the text. Further, although previous studies proposed the selective gate to control the information flow from the encoder to the decoder, it is static during the decoding and cannot differentiate the information based on the decoder states. In this paper, we propose a novel neural architecture for document summarization. Our approach has the following contributions: first, we incorporate syntactic information such as constituency parsing trees into the encoding sequence to learn both the semantic and syntactic information from the document, resulting in more accurate summary; second, we propose a dynamic gate network to select the salient information based on the context of the decoder state, which is essential to document summarization. The proposed model has been evaluated on CNN/Daily Mail summarization datasets and the experimental results show that the proposed approach outperforms baseline approaches., Comment: IJCNN 2019

Abstractive text summarization is a challenging task, and one need to design a mechanism to effectively extract salient information from the source text and then generate a summary. A parsing process of the source text contains critical syntactic or semantic structures, which is useful to generate more accurate summary. However, modeling a parsing tree for text summarization is not trivial due to its non-linear structure and it is harder to deal with a document that includes multiple sentences and their parsing trees. In this paper, we propose to use a graph to connect the parsing trees from the sentences in a document and utilize the stacked graph convolutional networks (GCNs) to learn the syntactic representation for a document. The selective attention mechanism is used to extract salient information in semantic and structural aspect and generate an abstractive summary. We evaluate our approach on the CNN/Daily Mail text summarization dataset. The experimental results show that the proposed GCNs based selective attention approach outperforms the baselines and achieves the state-of-the-art performance on the dataset., Comment: ICASSP 2020

Multimodalities provide promising performance than unimodality in most tasks. However, learning the semantic of the representations from multimodalities efficiently is extremely challenging. To tackle this, we propose the Transformer based Cross-modal Translator (TCT) to learn unimodal sequence representations by translating from other related multimodal sequences on a supervised learning method. Combined TCT with Multimodal Transformer Network (MTN), we evaluate MTN-TCT on the video-grounded dialogue which uses multimodality. The proposed method reports new state-of-the-art performance on video-grounded dialogue which indicates representations learned by TCT are more semantics compared to directly use unimodality., Comment: submitted to ICASSP 2020

Speech recognition technologies are gaining enormous popularity in various industrial applications. However, building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, an unsupervised pre-training method called Masked Predictive Coding is proposed, which can be applied for unsupervised pre-training with Transformer based model. Experiments on HKUST show that using the same training data, we can achieve CER 23.3%, exceeding the best end-to-end model by over 0.2% absolute CER. With more pre-training data, we can further reduce the CER to 21.0%, or a 11.8% relative CER reduction over baseline., Comment: Submitted to ICASSP 2020

Acoustic scene classification (ASC) and acoustic event detection (AED) are different but related tasks. Acoustic events can provide useful information for recognizing acoustic scenes. However, most of the datasets are provided without either the acoustic event or scene labels. To utilize the acoustic event information to improve the performance of ASC tasks, we present the cross-task pre-training mechanism which utilizes acoustic event information from the pre-trained AED model for ASC tasks. On the other hand, most of the models were designed and implemented on platforms with rich computing resources, and the on-device applications were limited. To solve this problem, we use model distillation method to compress our cross-task model to enable on-device acoustic scene classification. In this paper, the cross-task models and their student model were trained and evaluated on two datasets: TAU Urban Acoustic Scenes 2019 dataset and TUT Acoustic Scenes 2017 dataset. Results have shown that cross-task pre-training mechanism can significantly improve the performance of ASC tasks. The performance of our best model improved relatively 9.5% in the TAU Urban Acoustic Scenes 2019 dataset, and also improved 10% in the TUT Acoustic Scenes 2017 dataset compared with the official baseline. At the same time, the performance of the student model is much better than that of the model without teachers., Comment: presented at Interspeech workshop 2020

Speech emotion recognition is a challenging problem because human convey emotions in subtle and complex ways. For emotion recognition on human speech, one can either extract emotion related features from audio signals or employ speech recognition techniques to generate text from speech and then apply natural language processing to analyze the sentiment. Further, emotion recognition will be beneficial from using audio-textual multimodal information, it is not trivial to build a system to learn from multimodality. One can build models for two input sources separately and combine them in a decision level, but this method ignores the interaction between speech and text in the temporal domain. In this paper, we propose to use an attention mechanism to learn the alignment between speech frames and text words, aiming to produce more accurate multimodal feature representations. The aligned multimodal features are fed into a sequential model for emotion recognition. We evaluate the approach on the IEMOCAP dataset and the experimental results show the proposed approach achieves the state-of-the-art performance on the dataset., Comment: InterSpeech 2019

In this paper we present DELTA, a deep learning based language technology platform. DELTA is an end-to-end platform designed to solve industry level natural language and speech processing problems. It integrates most popular neural network models for training as well as comprehensive deployment tools for production. DELTA aims to provide easy and fast experiences for using, deploying, and developing natural language processing and speech models for both academia and industry use cases. We demonstrate the reliable performance with DELTA on several natural language processing and speech tasks, including text classification, named entity recognition, natural language inference, speech recognition, speaker verification, etc. DELTA has been used for developing several state-of-the-art algorithms for publications and delivering real production to serve millions of users., Comment: White paper for an open source library: https://github.com/didi/delta. 13 pages, 3 figures

Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue. End-to-end automatic speech recognition (ASR) simplifies the building of ASR systems considerably by predicting graphemes or characters directly from acoustic input. In the mean time, the need of expert linguistic knowledge is also eliminated, which makes it an attractive choice for code-switching ASR. This paper presents a hybrid CTC-Attention based end-to-end Mandarin-English code-switching (CS) speech recognition system and studies the effect of hybrid CTC-Attention based models, different modeling units, the inclusion of language identification and different decoding strategies on the task of code-switching ASR. On the SEAME corpus, our system achieves a mixed error rate (MER) of 34.24%., Comment: 5 pages, submitted to ICASSP 2019

End-To-End speech recognition have become increasingly popular in mandarin speech recognition and achieved delightful performance. Mandarin is a tonal language which is different from English and requires special treatment for the acoustic modeling units. There have been several different kinds of modeling units for mandarin such as phoneme, syllable and Chinese character. In this work, we explore two major end-to-end models: connectionist temporal classification (CTC) model and attention based encoder-decoder model for mandarin speech recognition. We compare the performance of three different scaled modeling units: context dependent phoneme(CDP), syllable with tone and Chinese character. We find that all types of modeling units can achieve approximate character error rate (CER) in CTC model and the performance of Chinese character attention model is better than syllable attention model. Furthermore, we find that Chinese character is a reasonable unit for mandarin speech recognition. On DidiCallcenter task, Chinese character attention model achieves a CER of 5.68% and CTC model gets a CER of 7.29%, on the other DidiReading task, CER are 4.89% and 5.79%, respectively. Moreover, attention model achieves a better performance than CTC model on both datasets., Comment: 5 pages

We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. The embeddings generated by Deep Speaker can be used for many tasks, including speaker identification, verification, and clustering. We experiment with ResCNN and GRU architectures to extract the acoustic features, then mean pool to produce utterance-level speaker embeddings, and train using triplet loss based on cosine similarity. Experiments on three distinct datasets suggest that Deep Speaker outperforms a DNN-based i-vector baseline. For example, Deep Speaker reduces the verification equal error rate by 50% (relatively) and improves the identification accuracy by 60% (relatively) on a text-independent dataset. We also present results that suggest adapting from a model trained with Mandarin can improve accuracy for English speaker recognition.

Most existing sequence labelling models rely on a fixed decomposition of a target sequence into a sequence of basic units. These methods suffer from two major drawbacks: 1) the set of basic units is fixed, such as the set of words, characters or phonemes in speech recognition, and 2) the decomposition of target sequences is fixed. These drawbacks usually result in sub-optimal performance of modeling sequences. In this pa- per, we extend the popular CTC loss criterion to alleviate these limitations, and propose a new loss function called Gram-CTC. While preserving the advantages of CTC, Gram-CTC automatically learns the best set of basic units (grams), as well as the most suitable decomposition of tar- get sequences. Unlike CTC, Gram-CTC allows the model to output variable number of characters at each time step, which enables the model to capture longer term dependency and improves the computational efficiency. We demonstrate that the proposed Gram-CTC improves CTC in terms of both performance and efficiency on the large vocabulary speech recognition task at multiple scales of data, and that with Gram-CTC we can outperform the state-of-the-art on a standard speech benchmark., Comment: Published at ICML 2017

Long short-term memory (LSTM) recurrent neural networks (RNNs) have been shown to give state-of-the-art performance on many speech recognition tasks, as they are able to provide the learned dynamically changing contextual window of all sequence history. On the other hand, the convolutional neural networks (CNNs) have brought significant improvements to deep feed-forward neural networks (FFNNs), as they are able to better reduce spectral variation in the input signal. In this paper, a network architecture called as convolutional recurrent neural network (CRNN) is proposed by combining the CNN and LSTM RNN. In the proposed CRNNs, each speech frame, without adjacent context frames, is organized as a number of local feature patches along the frequency axis, and then a LSTM network is performed on each feature patch along the time axis. We train and compare FFNNs, LSTM RNNs and the proposed LSTM CRNNs at various number of configurations. Experimental results show that the LSTM CRNNs can exceed state-of-the-art speech recognition performance., Comment: Published in INTERSPEECH 2015, September 6-10, 2015, Dresden, Germany

Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on LSTM are investigated considering that deep hierarchical model has turned out to be more efficient than a shallow one. Motivated by previous research on constructing deep recurrent neural networks (RNNs), alternative deep LSTM architectures are proposed and empirically evaluated on a large vocabulary conversational telephone speech recognition task. Meanwhile, regarding to multi-GPU devices, the training process for LSTM networks is introduced and discussed. Experimental results demonstrate that the deep LSTM networks benefit from the depth and yield the state-of-the-art performance on this task., Comment: submitted to ICASSP 2015 which does not perform blind reviews