Transformer with Bidirectional Decoder for Speech Recognition
Tsinghua University（清华大学）；ShanghaiTech University（上海科技大学）；Tsingmicro Intelligent Technology Co., Limited（清微智能科技有限公司）；Beijing National Research Center For Information Science And Technology（北京国家信息科学与技术研究中心）
Xi Chen, Songyang Zhang, Dandan Song, Peng Ouyang, Shouyi Yin
Attention-based models have made tremendous progress on end-to-end automatic speech recognition(ASR) recently. However, the conventional transformer-based approaches usually generate the sequence results token by token from left to right, leaving the right-to-left contexts unexploited. In this work, we introduce a bidirectional speech transformer to utilize the different directional contexts simultaneously. Specifically, the outputs of our proposed transformer include a left-to-right target, and a right-to-left target. In inference stage, we use the introduced bidirectional beam search method, which can not only generate left-to-right candidates but also generate right-to-left candidates, and determine the best hypothesis by the score.
To demonstrate our proposed speech transformer with a bidirectional decoder(STBD), we conduct extensive experiments on the AISHELL-1 dataset. The results of experiments show that STBD achieves a 3.6\% relative CER reduction(CERR) over the unidirectional speech transformer baseline. Besides, the strongest model in this paper called STBD-Big can achieve 6.64\% CER on the test set, without language model rescoring and any extra data augmentation strategies.
Southern University of Science and Technology（南方科技大学）；The Hong Kong Polytechnic University（香港理工大学）；Tongji University（同济大学）；Microsoft（微软）；Peng Cheng Laboratory（鹏城实验室）
Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text mod…
We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The pre-trained networks can then be fine-tuned on a smaller amount of supervised data for speech recognition. Experiments with this approach on the LibriSpeech and Wall Street Journal corpora show promising results. We find that the main factors that lead to speech recognition improvements are: masking segments of sufficient width in both time and frequency, pre…
Stuttering is a speech impediment affecting tens of millions of people on an everyday basis. Even with its commonality, there is minimal data and research on the identification and classification of stuttered speech. This paper tackles the problem of detection and classification of different forms of stutter. As opposed to most existing works that identify stutters with language models, our work proposes a model that relies solely on acoustic features, allowing for identification of several variations of stutter disfluencies without the need for speech recognition. Our model uses a deep residu…
In this paper, we propose a simple but effective method to decode the output of Connectionist Temporal Classifier (CTC) model using a bi-directional neural language model. The bidirectional language model uses the future as well as the past information in order to predict the next output in the sequence. The proposed method based on bi-directional beam search takes advantage of the CTC greedy decoding output to represent the noisy future information. Experiments on the Librispeechdataset demonstrate the superiority of our proposed method compared to baselines using unidirectional decoding. In …
Xinjiang University（新疆大学）；Bytedance AI Lab（字节跳动人工智能实验室）；Nanyang Technological University（南洋理工大学）；National Institute of Information and Communications Technology（日本国立信息与通信技术研究所）
To let the state-of-the-art end-to-end ASR model enjoy data efficiency, as well as much more unpaired text data by multi-modal training, one needs to address two problems: 1) the synchronicity of feature sampling rates between speech and language (aka text data); 2) the homogeneity of the learned representations from two encoders. In this paper we propose to employ a novel bidirectional attention mechanism (BiAM) to jointly learn both ASR encoder (bottom layers) and text encoder with a multi-modal learning method. The BiAM is to facilitate feature sampling rate exchange, realizing the quality …
University of Science and Technology Beijing（北京科技大学）；Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education（教育部工业过程知识自动化重点实验室）；EEasy Technology Company Ltd.（易捷科技有限公司）
Non-autoregressive (NAR) transformer models have been studied intensively in automatic speech recognition (ASR), and a substantial part of NAR transformer models is to use the casual mask to limit token dependencies. However, the casual mask is designed for the left-to-right decoding process of the non-parallel autoregressive (AR) transformer, which is inappropriate for the parallel NAR transformer since it ignores the right-to-left contexts. Some models are proposed to utilize right-to-left contexts with an extra decoder, but these methods increase the model complexity. To tackle the above pr…
We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech recognition task -- transcribing audio inputs into pseudo subword sequences. This process stands on its own, or can be applied as low-cost second-stage pre-training. We experiment with automatic speech recognition (ASR), spoken named entity recognition, and speech-to-text translation. We set new state-of-the-art results for end-to-end spoken named entity recogni…
We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et al., 2017) but consist of two decoders, each responsible for one task (ASR or ST). Our major contribution lies in how these decoders interact with each other: one decoder can attend to different information sources from the other via a dual-attention mechanism. We propose two variants of these architectures corresponding to two different levels of dependencies …
In automatic speech recognition, many studies have shown performance improvements using language models (LMs). Recent studies have tried to use bidirectional LMs (biLMs) instead of conventional unidirectional LMs (uniLMs) for rescoring the $N$-best list decoded from the acoustic model. In spite of their theoretical benefits, the biLMs have not given notable improvements compared to the uniLMs in their experiments. This is because their biLMs do not consider the interaction between the two directions. In this paper, we propose a novel sentence scoring method considering the interaction between …
This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the encoder-decoder network using acoustic units, i.e., pseudo codes, derived from an offline clustering model. One is to predict the pseudo codes via masked language modeling in encoder output, like HuBERT model, while the other lets the decoder learn to reconstruct pseudo codes autoregressively instead of generating textual scripts. In this way, the decoder learns to…
Beijing University of Posts and Telecommunications（北京邮电大学）；Tsinghua University（清华大学）；Sogou Inc.（搜狗公司）
Attention-based end-to-end models such as Listen, Attend and Spell (LAS), simplify the whole pipeline of traditional automatic speech recognition (ASR) systems and become popular in the field of speech recognition. In previous work, researchers have shown that such architectures can acquire comparable results to state-of-the-art ASR systems, especially when using a bidirectional encoder and global soft attention (GSA) mechanism. However, bidirectional encoder and GSA are two obstacles for real-time speech recognition. In this work, we aim to stream LAS baseline by removing the above two obstac…
Transformer-based models have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. This work proposes a dual-decoder transformer model for low-resource multilingual speech recognition for Indian languages. Our proposed model consists of a Conformer [1] encoder, two parallel transformer decoders, and a language classifier. We use a phoneme decoder (PHN-DEC) for the phoneme recognition task and a grapheme decoder (GRP-DEC) to predict grapheme sequence along with language information. We consider phoneme recognition and language id…
We present a comprehensive study of deep bidirectional long short-term memory (LSTM) recurrent neural network (RNN) based acoustic models for automatic speech recognition (ASR). We study the effect of size and depth and train models of up to 8 layers. We investigate the training aspect and study different variants of optimization methods, batching, truncated backpropagation, different regularization techniques such as dropout and $L_2$ regularization, and different gradient clipping variants. The major part of the experimental analysis was performed on the Quaero corpus. Additional experiments…
TV subtitles are a rich source of transcriptions of many types of speech, ranging from read speech in news reports to conversational and spontaneous speech in talk shows and soaps. However, subtitles are not verbatim (i.e. exact) transcriptions of speech, so they cannot be used directly to improve an Automatic Speech Recognition (ASR) model. We propose a multitask dual-decoder Transformer model that jointly performs ASR and automatic subtitling. The ASR decoder (possibly pre-trained) predicts the verbatim output and the subtitle decoder generates a subtitle, while sharing the encoder. The two …
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an acoustic encoder renders the language model from ground-truth sequences in an auto-regressive manner during training. However, the training corpus of the decoder is limited to the speech transcriptions, which is far less than the corpus needed to train an acceptable language model. This leads to poor robustness of decoder. To alleviate this problem, we propose…
Automatic speech recognition (ASR) systems developed in recent years have shown promising results with self-attention models (e.g., Transformer and Conformer), which are replacing conventional recurrent neural networks. Meanwhile, a structured state space model (S4) has been recently proposed, producing promising results for various long-sequence modeling tasks, including raw speech classification. The S4 model can be trained in parallel, same as the Transformer model. In this study, we applied S4 as a decoder for ASR and text-to-speech (TTS) tasks by comparing it with the Transformer decoder.…
Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition tasks, due to their efficient representation of long and short term dependencies in sequences of inter-dependent features. Nonetheless, internal dependencies within the element composing multidimensional features are weakly considered by traditional real-valued representations. We propose a novel quaternion long-short term memory (QLSTM) recurrent neural netw…
Mobvoi Inc.（出门问问公司）；WeNet Open Source Community（WeNet开源社区）
The unified streaming and non-streaming two-pass (U2) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy, real-time factor (RTF), and latency. In this paper, we present U2++, an enhanced version of U2 to further improve the accuracy. The core idea of U2++ is to use the forward and the backward information of the labeling sequences at the same time at training to learn richer information, and combine the forward and backward prediction at decoding to give more accurate recognition results. We also proposed a new data augmentation metho…
In this paper, we propose a novel multi-modal multi-task encoder-decoder pre-training framework (MMSpeech) for Mandarin automatic speech recognition (ASR), which employs both unlabeled speech and text data. The main difficulty in speech-text joint pre-training comes from the significant difference between speech and text modalities, especially for Mandarin speech and text. Unlike English and other languages with an alphabetic writing system, Mandarin uses an ideographic writing system where character and sound are not tightly mapped to one another. Therefore, we propose to introduce the phonem…
The multi-decoder (MD) end-to-end speech translation model has demonstrated high translation quality by searching for better intermediate automatic speech recognition (ASR) decoder states as hidden intermediates (HI). It is a two-pass decoding model decomposing the overall task into ASR and machine translation sub-tasks. However, the decoding speed is not fast enough for real-world applications because it conducts beam search for both sub-tasks during inference. We propose Fast-MD, a fast MD model that generates HI by non-autoregressive (NAR) decoding based on connectionist temporal classifica…
University of Science and Technology of China（中国科学技术大学）；Microsoft（微软）；Microsoft Research Asia（微软亚洲研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
The rapid development of single-modal pre-training has prompted researchers to pay more attention to cross-modal pre-training methods. In this paper, we propose a unified-modal speech-unit-text pre-training model, SpeechUT, to connect the representations of a speech encoder and a text decoder with a shared unit encoder. Leveraging hidden-unit as an interface to align speech and text, we can decompose the speech-to-text model into a speech-to-unit model and a unit-to-text model, which can be jointly pre-trained with unpaired speech and text data respectively. Our proposed SpeechUT is fine-tuned…
We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech recognition. Unlike standard one-pass decoding with on-the-fly composition decoder which might induce a significant computation overhead, the asynchronous dynamic decoder has a novel design where it has two fronts, with one performing "exploration" and the other "backfill". The computation of the two fronts alternates in the decoding process, resulting in more effective pruning than the standard one-pass decoding wi…
Transformers have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. In this work, we propose a multi-task learning-based transformer model for low-resource multilingual speech recognition for Indian languages. Our proposed model consists of a conformer [1] encoder and two parallel transformer decoders. We use a phoneme decoder (PHN-DEC) for the phoneme recognition task and a grapheme decoder (GRP-DEC) to predict grapheme sequence. We consider the phoneme recognition task as an auxiliary task for our multi-task learning framew…
MTLM: Incorporating Bidirectional Text Information to Enhance Language Model Training in Speech Recognition Systems
Princeton University, Princeton NJ 08544, USA, , WWW home page: http://users/ iekeland/web/welcome.html Universit\' e de Paris-Sud, Laboratoire d'Analyse Num\' e rique, B\ a timent 425, F-91405 Orsay Cedex, France；Megatronix, Beijing, China Baidu, Inc., Beijing, China Shumei AI Research Institute, Beijing China Newcastle University, Newcastle Upon Tyne, United Kingdom
The recent developments in technology have re-warded us with amazing audio synthesis models like TACOTRON and WAVENETS. On the other side, it poses greater threats such as speech clones and deep fakes, that may go undetected. To tackle these alarming situations, there is an urgent need to propose models that can help discriminate a synthesized speech from an actual human speech and also identify the source of such a synthesis. Here, we propose a model based on Convolutional Neural Network (CNN) and Bidirectional Recurrent Neural Network (BiRNN) that helps to achieve both the aforementioned obj…
Language models (LMs) pre-trained on massive amounts of text, in particular bidirectional encoder representations from Transformers (BERT), generative pre-training (GPT), and GPT-2, have become a key technology for many natural language processing tasks. In this paper, we present results using fine-tuned GPT, GPT-2, and their combination for automatic speech recognition (ASR). Unlike unidirectional LM GPT and GPT-2, BERT is bidirectional whose direct product of the output probabilities is no longer a valid language prior probability. A conversion method is proposed to compute the correct langu…
While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation problems, resulting from irregular pausing patterns or slow speakers. Transformer sequence tagging models are effective at capturing long bi-directional context, which is crucial for automatic punctuation. Automatic Speech Recognition (ASR) production systems, however, are constrained by real-time requirements, making it hard to incorporate the right context when making punctua…
Toyohashi University of Technology（丰桥技术科学大学）；Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室（MERL））；Johns Hopkins University（约翰斯·霍普金斯大学）
Attention-based encoder decoder network uses a left-to-right beam search algorithm in the inference step. The current beam search expands hypotheses and traverses the expanded hypotheses at the next time step. This traversal is implemented using a for-loop program in general, and it leads to speed down of the recognition process. In this paper, we propose a parallelism technique for beam search, which accelerates the search process by vectorizing multiple hypotheses to eliminate the for-loop program. We also propose a technique to batch multiple speech utterances for off-line recognition use, …
Improving end-to-end speech recognition by incorporating external text data has been a longstanding research topic. There has been a recent focus on training E2E ASR models that get the performance benefits of external text data without incurring the extra cost of evaluating an external language model at inference time. In this work, we propose training ASR model jointly with a set of text-to-text auxiliary tasks with which it shares a decoder and parts of the encoder. When we jointly train ASR and masked language model with the 960-hour Librispeech and Opensubtitles data respectively, we obse…
National Taiwan University（台湾大学）；University of California, San Diego（加州大学圣地亚哥分校）
In this paper, we investigate the benefit that off-the-shelf word embedding can bring to the sequence-to-sequence (seq-to-seq) automatic speech recognition (ASR). We first introduced the word embedding regularization by maximizing the cosine similarity between a transformed decoder feature and the target word embedding. Based on the regularized decoder, we further proposed the fused decoding mechanism. This allows the decoder to consider the semantic consistency during decoding by absorbing the information carried by the transformed decoder feature, which is learned to be close to the target w…
The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding efficiency of Conformer, we propose a novel connectionist temporal summarization (CTS) method that reduces the number of frames required for the attention decoder fed from the acoustic sequences generated by the encoder, thus reducing operations. However, to achieve such decoding improvements, we must fine-tune model parameters, as cross-attention observations …
We present an optimized weighted finite-state transducer (WFST) decoder capable of online streaming and offline batch processing of audio using Graphics Processing Units (GPUs). The decoder is efficient in memory utilization, input/output (I/O) bandwidth, and uses a novel Viterbi implementation designed to maximize parallelism. The reduced memory footprint allows the decoder to process significantly larger graphs than previously possible, while optimizing I/O increases the number of simultaneous streams supported. GPU preprocessing of lattice segments enables intermediate lattice results to be…
Robust voice activity detection (VAD) is a challenging task in low signal-to-noise (SNR) environments. Recent studies show that speech enhancement is helpful to VAD, but the performance improvement is limited. To address this issue, here we propose a speech enhancement aided end-to-end multi-task model for VAD. The model has two decoders, one for speech enhancement and the other for VAD. The two decoders share the same encoder and speech separation network. Unlike the direct thought that takes two separated objectives for VAD and speech enhancement respectively, here we propose a new joint opt…
Toyota Technological Institute at Chicago（芝加哥丰田理工学院）；Google Inc.（谷歌公司）
Attention-based recurrent neural encoder-decoder models present an elegant solution to the automatic speech recognition problem. This approach folds the acoustic model, pronunciation model, and language model into a single network and requires only a parallel corpus of speech and text for training. However, unlike in conventional approaches that combine separate acoustic and language models, it is not clear how to use additional (unpaired) text. While there has been previous work on methods addressing this problem, a thorough comparison among methods is still lacking. In this paper, we compare…
On the compression of shallow non-causal ASR models using knowledge distillation and tied-and-reduced decoder for low-latency on-device speech recognition
College of Information Engineering, Tarim University（塔里木大学信息工程学院）
Uyghur is a minority language, and its resources for Automatic Speech Recognition (ASR) research are always insufficient. THUYG-20 is currently the only open-sourced dataset of Uyghur speeches. State-of-the-art results of its clean and noiseless speech test task haven't been updated since the first release, which shows a big gap in the development of ASR between mainstream languages and Uyghur. In this paper, we try to bridge the gap by ultimately optimizing the ASR systems, and by developing a morpheme-based decoder, MLDG-Decoder (Morpheme Lattice Dynamically Generating Decoder for Uyghur DNN…
