This study (The work was accomplished during the internship in Tencent AI lab) addresses semi-supervised acoustic modeling, i.e. attaining high-level representations from unsupervised audio data and fine-tuning the parameters of pre-trained model with supervised data. The proposed approach adopts a two-stage training framework, consisting of masked pre-trained encoder (MPE) and Joint CTC-Transformer (JCT). In the MPE framework, part of input frames are masked and reconstructed after the encoder with massive unsupervised data. In JCT framework, compared with original Transformer, acoustic features are applied as input instead of plain text. CTC loss performs as the prediction target on top of the encoder, and decoder blocks remain unchanged. This paper presents a comparison between two-stage training method and the fully supervised JCT. In addition, this paper investigates the our approach's robustness against different volumns of training data. Experiments on the two-stage training method deliver much better performance than fully supervised model. The word error rate (WER) with two-stage training which only exploits 30\% of WSJ labeled data achieves 17\% reduction than which trained by 50\% of WSJ in a fully supervised way. Moreover, increasing unlabeled data for MPE from WSJ (81h) to Librispeech (960h) attains about 22\% WER reduction.
Graduate School of Informatics, Kyoto University（京都大学信息学研究生院）
Connectionist temporal classification (CTC) -based models are attractive in automatic speech recognition (ASR) because of their non-autoregressive nature. To take advantage of text-only data, language model (LM) integration approaches such as rescoring and shallow fusion have been widely used for CTC. However, they lose CTC's non-autoregressive nature because of the need for beam search, which slows down the inference speed. In this study, we propose an error correction method with phone-conditioned masked LM (PC-MLM). In the proposed method, less confident word tokens in a greedy decoded outp…
Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupervised way, making it less accurate and difficult to interpret. We propose two supervision-guided codebook generation approaches to improve automatic speech recognition (ASR) performance and also the pre-training efficiency, either through decoding with a hybrid ASR system to generate phoneme-level alignments (named PBERT), or performing clustering on the supervised speech features extracted from an end-to-end CTC mo…
Recently, end-to-end speech recognition with a hybrid model consisting of the connectionist temporal classification(CTC) and the attention encoder-decoder achieved state-of-the-art results. In this paper, we propose a novel CTC decoder structure based on the experiments we conducted and explore the relation between decoding performance and the depth of encoder. We also apply attention smoothing mechanism to acquire more context information for subword-based decoding. Taken together, these strategies allow us to achieve a word error rate(WER) of 4.43% without LM and 3.34% with RNN-LM on the tes…
We present BERT-CTC-Transducer (BECTRA), a novel end-to-end automatic speech recognition (E2E-ASR) model formulated by the transducer with a BERT-enhanced encoder. Integrating a large-scale pre-trained language model (LM) into E2E-ASR has been actively studied, aiming to utilize versatile linguistic knowledge for generating accurate text. One crucial factor that makes this integration challenging lies in the vocabulary mismatch; the vocabulary constructed for a pre-trained LM is generally too large for E2E-ASR training and is likely to have a mismatch against a target ASR domain. To overcome s…
This article describes an efficient training method for online streaming attention-based encoder-decoder (AED) automatic speech recognition (ASR) systems. AED models have achieved competitive performance in offline scenarios by jointly optimizing all components. They have recently been extended to an online streaming framework via models such as monotonic chunkwise attention (MoChA). However, the elaborate attention calculation process is not robust for long-form speech utterances. Moreover, the sequence-level training objective and time-restricted streaming encoder cause a nonnegligible delay…
In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T. In transcribing social media videos of 7 languages with training data 3K-14K hours, we conduct large-scale controlled experimentation across each criterion using identical datasets and encoder model architecture. We find that RNN-T has consistent wins in ASR accuracy, while CTC models excel at inference efficiency. Moreover, we selectively examine various modeling s…
We propose a novel method to accelerate training and inference process of recurrent neural network transducer (RNN-T) based on the guidance from a co-trained connectionist temporal classification (CTC) model. We made a key assumption that if an encoder embedding frame is classified as a blank frame by the CTC model, it is likely that this frame will be aligned to blank for all the partial alignments or hypotheses in RNN-T and it can be discarded from the decoder input. We also show that this frame reduction operation can be applied in the middle of the encoder, which result in significant spee…
Pruned CTC for Memory-Efficient Large-Vocabulary ASR Training
Shanghai Jiao Tong University（上海交通大学）；University of Cambridge（剑桥大学）；Tsinghua University（清华大学）；Alibaba Token Hub, Alibaba Group（阿里巴巴集团阿里通义实验室）；Nankai University（南开大学）；Chinese University of Hong Kong（香港中文大学）；SII（上海人工智能实验室）
This paper proposes CTC-based non-autoregressive ASR with self-conditioned folded encoders. The proposed method realizes non-autoregressive ASR with fewer parameters by folding the conventional stack of encoders into only two blocks; base encoders and folded encoders. The base encoders convert the input audio features into a neural representation suitable for recognition. This is followed by the folded encoders applied repeatedly for further refinement. Applying the CTC loss to the outputs of all encoders enforces the consistency of the input-output relationship. Thus, folded encoders learn to…
This paper proposes InterAug: a novel training method for CTC-based ASR using augmented intermediate representations for conditioning. The proposed method exploits the conditioning framework of self-conditioned CTC to train robust models by conditioning with "noisy" intermediate predictions. During the training, intermediate predictions are changed to incorrect intermediate predictions, and fed into the next layer for conditioning. The subsequent layers are trained to correct the incorrect intermediate predictions with the intermediate losses. By repeating the augmentation and the correction, …
Johns Hopkins University（约翰斯·霍普金斯大学）；Amazon（亚马逊）；Mitsubishi Electric Research Laboratories（三菱电机研究实验室）
Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end (E2E) Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing both architectures during multi-task training and joint decoding. In this work, we present a multi-stream framework based on joint CTC/Attention E2E ASR with parallel streams represented by separate encoders aiming to capture diverse information. On top of the regular attention networks, the Hierarchical Attention Network (HAN) is introduced to steer …
We present a simple and efficient auxiliary loss function for automatic speech recognition (ASR) based on the connectionist temporal classification (CTC) objective. The proposed objective, an intermediate CTC loss, is attached to an intermediate layer in the CTC encoder network. This intermediate CTC loss well regularizes CTC training and improves the performance requiring only small modification of the code and small and no overhead during training and inference, respectively. In addition, we propose to combine this intermediate CTC loss with stochastic depth training, and apply this combinat…
Northwestern Polytechnical University（西北工业大学）；Horizon Robotics（地平线机器人）；WeNet Open Source Community（WeNet开源社区）
Recently, the unified streaming and non-streaming two-pass (U2/U2++) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy and latency. In this paper, we present fast-U2++, an enhanced version of U2++ to further reduce partial latency. The core idea of fast-U2++ is to output partial results of the bottom layers in its encoder with a small chunk, while using a large chunk in the top layers of its encoder to compensate the performance degradation caused by the small chunk. Moreover, we use knowledge distillation method to reduce the token …
The RNN-Transducers and improved attention-based encoder-decoder models are widely applied to streaming speech recognition. Compared with these two end-to-end models, the CTC model is more efficient in training and inference. However, it cannot capture the linguistic dependencies between the output tokens. Inspired by the success of two-pass end-to-end models, we introduce a transformer decoder and the two-stage inference method into the streaming CTC model. During inference, the CTC decoder first generates many candidates in a streaming fashion. Then the transformer decoder selects the best c…
Amazon AI（亚马逊人工智能）；University of Washington（华盛顿大学）
The success of self-attention in NLP has led to recent applications in end-to-end encoder-decoder architectures for speech recognition. Separately, connectionist temporal classification (CTC) has matured as an alignment-free, non-autoregressive approach to sequence transduction, either by itself or in various multitask and decoding frameworks. We propose SAN-CTC, a deep, fully self-attentional network for CTC, and show it is tractable and competitive for end-to-end speech recognition. SAN-CTC trains quickly and outperforms existing CTC models and most encoder-decoder models, with character err…
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…
Non-autoregressive (NAR) transformer models have achieved significantly inference speedup but at the cost of inferior accuracy compared to autoregressive (AR) models in automatic speech recognition (ASR). Most of the NAR transformers take a fixed-length sequence filled with MASK tokens or a redundant sequence copied from encoder states as decoder input, they cannot provide efficient target-side information thus leading to accuracy degradation. To address this problem, we propose a CTC-enhanced NAR transformer, which generates target sequence by refining predictions of the CTC module. Experimen…
Tencent Cloud Xiaowei（腾讯云小微）；Institute of Acoustics, CAS（中国科学院声学研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Recently, end-to-end automatic speech recognition models based on connectionist temporal classification (CTC) have achieved impressive results, especially when fine-tuned from wav2vec2.0 models. Due to the conditional independence assumption, CTC-based models are always weaker than attention-based encoder-decoder models and require the assistance of external language models (LMs). To solve this issue, we propose two knowledge transferring methods that leverage pre-trained LMs, such as BERT and GPT2, to improve CTC-based models. The first method is based on representation learning, in which the…
Connectionist Temporal Classification (CTC) based end-to-end speech recognition system usually need to incorporate an external language model by using WFST-based decoding in order to achieve promising results. This is more essential to Mandarin speech recognition since it owns a special phenomenon, namely homophone, which causes a lot of substitution errors. The linguistic information introduced by language model will help to distinguish these substitution errors. In this work, we propose a transformer based spelling correction model to automatically correct errors especially the substitution …
Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）
There is often a trade-off between performance and latency in streaming automatic speech recognition (ASR). Traditional methods such as look-ahead and chunk-based methods, usually require information from future frames to advance recognition accuracy, which incurs inevitable latency even if the computation is fast enough. A causal model that computes without any future frames can avoid this latency, but its performance is significantly worse than traditional methods. In this paper, we propose corresponding revision strategies to improve the causal model. Firstly, we introduce a real-time encod…
This paper presents InterMPL, a semi-supervised learning method of end-to-end automatic speech recognition (ASR) that performs pseudo-labeling (PL) with intermediate supervision. Momentum PL (MPL) trains a connectionist temporal classification (CTC)-based model on unlabeled data by continuously generating pseudo-labels on the fly and improving their quality. In contrast to autoregressive formulations, such as the attention-based encoder-decoder and transducer, CTC is well suited for MPL, or PL-based semi-supervised ASR in general, owing to its simple/fast inference algorithm and robustness aga…
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…
This work describes an encoder pre-training procedure using frame-wise label to improve the training of streaming recurrent neural network transducer (RNN-T) model. Streaming RNN-T trained from scratch usually performs worse than non-streaming RNN-T. Although it is common to address this issue through pre-training components of RNN-T with other criteria or frame-wise alignment guidance, the alignment is not easily available in end-to-end manner. In this work, frame-wise alignment, used to pre-train streaming RNN-T's encoder, is generated without using a HMM-based system. Therefore an all-neura…
In recent years, End-to-End speech recognition technology based on deep learning has developed rapidly. Due to the lack of Turkish speech data, the performance of Turkish speech recognition system is poor. Firstly, this paper studies a series of speech recognition tuning technologies. The results show that the performance of the model is the best when the data enhancement technology combining speed perturbation with noise addition is adopted and the beam search width is set to 16. Secondly, to maximize the use of effective feature information and improve the accuracy of feature extraction, thi…
This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-supervised representation learning from audio spectrograms. Following the Transformer encoder-decoder design in MAE, our Audio-MAE first encodes audio spectrogram patches with a high masking ratio, feeding only the non-masked tokens through encoder layers. The decoder then re-orders and decodes the encoded context padded with mask tokens, in order to reconstruct the input spectrogram. We find it beneficial to incorporate local window attention in the decoder, as audio spectrograms are highly correlated in lo…
Masked language model (MLM) has been widely used for understanding tasks, e.g. BERT. Recently, MLM has also been used for generation tasks. The most popular one in speech is using Mask-CTC for non-autoregressive speech recognition. In this paper, we take one step further, and explore the possibility of using MLM as a non-autoregressive spell correction (SC) model for transformer-transducer (TT), denoted as MLM-SC. Our initial experiments show that MLM-SC provides no improvements on Librispeech data. The problem might be the choice of modeling units (word pieces) and the inaccuracy of the TT co…
University of Chinese Academy of Sciences（中国科学院大学）
Recently, Transformer has gained success in automatic speech recognition (ASR) field. However, it is challenging to deploy a Transformer-based end-to-end (E2E) model for online speech recognition. In this paper, we propose the Transformer-based online CTC/attention E2E ASR architecture, which contains the chunk self-attention encoder (chunk-SAE) and the monotonic truncated attention (MTA) based self-attention decoder (SAD). Firstly, the chunk-SAE splits the speech into isolated chunks. To reduce the computational cost and improve the performance, we propose the state reuse chunk-SAE. Sencondly…
In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that the multi-task training not only tackles the complexity of optimizing CTC models such as acoustic-to-word but also results in significant improvement compared to the plain-task training with an optimal setup. Furthermore, we propose to use the encoding representation learned by the multi-task network to initialize the encoder of attention-based models. Thereb…
We consider the design of two-pass voice trigger detection systems. We focus on the networks in the second pass that are used to re-score candidate segments obtained from the first-pass. Our baseline is an acoustic model(AM), with BiLSTM layers, trained by minimizing the CTC loss. We replace the BiLSTM layers with self-attention layers. Results on internal evaluation sets show that self-attention networks yield better accuracy while requiring fewer parameters. We add an auto-regressive decoder network on top of the self-attention layers and jointly minimize the CTC loss on the encoder and the …
In this paper, we propose a simple yet powerful improvement over the recent Self-Supervised Audio Spectrogram Transformer (SSAST) model for speech and audio classification. Specifically, we leverage the insight that the SSAST uses a very high masking ratio (75%) during pretraining, meaning that the vast majority of self-attention compute is performed on mask tokens. We address this by integrating the encoder-decoder architecture from Masked Autoencoders are Scalable Vision Learners (MAE) into the SSAST, where a deep encoder operates on only unmasked input, and a shallow decoder operates on enc…
MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection
National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China（中国科学技术大学国家语音语言信息处理工程研究中心）；ICT Cluster, Singapore Institute of Technology（新加坡理工学院ICT集群）；The Australian National University（澳大利亚国立大学）
The two most common paradigms for end-to-end speech recognition are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models. It has been argued that the latter is better suited for learning an implicit language model. We test this hypothesis by measuring temporal context sensitivity and evaluate how the models perform when we constrain the amount of contextual information in the audio input. We find that the AED model is indeed more context sensitive, but that the gap can be closed by adding self-attention to the CTC model. Furthermore, the two models perfo…
