Semi-supervised learning has demonstrated promising results in automatic speech recognition (ASR) by self-training using a seed ASR model with pseudo-labels generated for unlabeled data. The effectiveness of this approach largely relies on the pseudo-label accuracy, for which typically only the 1-best ASR hypothesis is used. However, alternative ASR hypotheses of an N-best list can provide more accurate labels for an unlabeled speech utterance and also reflect uncertainties of the seed ASR model. In this paper, we propose a generalized form of the connectionist temporal classification (CTC) objective that accepts a graph representation of the training targets. The newly proposed graph-based temporal classification (GTC) objective is applied for self-training with WFST-based supervision, which is generated from an N-best list of pseudo-labels. In this setup, GTC is used to learn not only a temporal alignment, similarly to CTC, but also a label alignment to obtain the optimal pseudo-label sequence from the weighted graph. Results show that this approach can effectively exploit an N-best list of pseudo-labels with associated scores, outperforming standard pseudo-labeling by a large margin, with ASR results close to an oracle experiment in which the best hypotheses of the N-best lists are selected manually.
This paper presents a brief survey on Automatic Speech Recognition and discusses the major themes and advances made in the past 60 years of research, so as to provide a technological perspective and an appreciation of the fundamental progress that has been accomplished in this important area of speech communication. After years of research and development the accuracy of automatic speech recognition remains one of the important research challenges (e.g., variations of the context, speakers, and environment).The design of Speech Recognition system requires careful attentions to the following issues: Definition of various types of speech classes, speech representation, feature extraction techniques, speech classifiers, database and performance evaluation. The problems that are existing in ASR and the various techniques to solve these problems constructed by various research workers have been presented in a chronological order. Hence authors hope that this work shall be a contribution in the area of speech recognition. The objective of this review paper is to summarize and compare some of the well known methods used in various stages of speech recognition system and identify research topic and applications which are at the forefront of this exciting and challenging field.
Traditional visual speech recognition systems consist of two stages, feature extraction and classification. Recently, several deep learning approaches have been presented which automatically extract features from the mouth images and aim to replace the feature extraction stage. However, research on joint learning of features and classification remains limited. In addition, most of the existing methods require large amounts of data in order to achieve state-of-the-art performance, otherwise they under-perform. In this work, we present an end-to-end visual speech recognition system based on fully-connected layers and Long-Short Memory (LSTM) networks which is suitable for small-scale datasets. The model consists of two streams which extract features directly from the mouth and difference images, respectively. The temporal dynamics in each stream are modelled by a Bidirectional LSTM (BLSTM) and the fusion of the two streams takes place via another BLSTM. An absolute improvement of 0.6%, 3.4%, 3.9%, 11.4% over the state-of-the-art is reported on the OuluVS2, CUAVE, AVLetters and AVLetters2 databases, respectively.
Optimization of modern ASR architectures is among the highest priority tasks since it saves many computational resources for model training and inference. The work proposes a new Uconv-Conformer architecture based on the standard Conformer model that consistently reduces the input sequence length by 16 times, which results in speeding up the work of the intermediate layers. To solve the convergence problem with such a significant reduction of the time dimension, we use upsampling blocks similar to the U-Net architecture to ensure the correct CTC loss calculation and stabilize network training. The Uconv-Conformer architecture appears to be not only faster in terms of training and inference but also shows better WER compared to the baseline Conformer. Our best Uconv-Conformer model showed 40.3% epoch training time reduction, 47.8%, and 23.5% inference acceleration on the CPU and GPU, respectively. Relative WER on Librispeech test_clean and test_other decreased by 7.3% and 9.2%.
Automatic speech recognition (ASR) in the cloud allows the use of larger models and more powerful multi-channel signal processing front-ends compared to on-device processing. However, it also adds an inherent latency due to the transmission of the audio signal, especially when transmitting multiple channels of a microphone array. One way to reduce the network bandwidth requirements is client-side compression with a lossy codec such as Opus. However, this compression can have a detrimental effect especially on multi-channel ASR front-ends, due to the distortion and loss of spatial information introduced by the codec. In this publication, we propose an improved approach for the compression of microphone array signals based on Opus, using a modified joint channel coding approach and additionally introducing a multi-channel spatial decorrelating transform to reduce redundancy in the transmission. We illustrate the effect of the proposed approach on the spatial information retained in multi-channel signals after compression, and evaluate the performance on far-field ASR with a multi-channel beamforming front-end. We demonstrate that our approach can lead to a 37.5 % bitrate reduction or a 5.1 % relative word error rate reduction for a fixed bitrate budget in a seven channel setup.
Recent work has shown that it is possible to train a single model to perform joint acoustic echo cancellation (AEC), speech enhancement, and voice separation, thereby serving as a unified frontend for robust automatic speech recognition (ASR). The joint model uses contextual information, such as a reference of the playback audio, noise context, and speaker embedding. In this work, we propose a number of novel improvements to such a model. First, we improve the architecture of the Cross-Attention Conformer that is used to ingest noise context into the model. Second, we generalize the model to be able to handle varying lengths of noise context. Third, we propose Signal Dropout, a novel strategy that models missing contextual information. In the absence of one or more signals, the proposed model performs nearly as well as task-specific models trained without these signals; and when such signals are present, our system compares well against systems that require all context signals. Over the baseline, the final model retains a relative word error rate reduction of 25.0% on background speech when speaker embedding is absent, and 61.2% on AEC when device playback is absent.
End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable and adaptive features and mitigate information loss, we propose a new encoder that adopts globally attentive locally recurrent (GALR) networks and directly takes raw waveform as input. We observe improved ASR performance and robustness by applying GALR on different window lengths to aggregate fine-grain temporal information into multi-scale acoustic features. Experiments are conducted on a benchmark dataset AISHELL-2 and two large-scale Mandarin speech corpus of 5,000 hours and 21,000 hours. With faster speed and comparable model size, our proposed multi-scale GALR waveform encoder achieved consistent character error rate reductions (CERRs) from 7.9% to 28.1% relative over strong baselines, including Conformer and TDNN-Conformer. In particular, our approach demonstrated notable robustness than the traditional handcrafted features and outperformed the baseline MFCC-based TDNN-Conformer model by a 15.2% CERR on a music-mixed real-world speech test set.
Undoubtedly, one of the most important issues in computer science is intelligent speech recognition. In these systems, computers try to detect and respond to the speeches they are listening to, like humans. In this research, presenting of a suitable method for the diagnosis of Persian phonemes by AI using the signal processing and classification algorithms have tried. For this purpose, the STFT algorithm has been used to process the audio signals, as well as to detect and classify the signals processed by the deep artificial neural network. At first, educational samples were provided as two phonological phrases in Persian language and then signal processing operations were performed on them. Then the results for the data training have been given to the artificial deep neural network. At the final stage, the experiment was conducted on new sounds.
Self-training (ST), or pseudo-labeling has sparked significant interest in the automatic speech recognition (ASR) community recently because of its success in harnessing unlabeled data. Unlike prior semi-supervised learning approaches that relied on iteratively regenerating pseudo-labels (PLs) from a trained model and using them to train a new model, recent state-of-the-art methods perform `continuous training' where PLs are generated using a very recent version of the model being trained. Nevertheless, these approaches still rely on bootstrapping the ST using an initial supervised learning phase where the model is trained on labeled data alone. We believe this has the potential for over-fitting to the labeled dataset in low resource settings and that ST from the start of training should reduce over-fitting. In this paper we show how we can do this by dynamically controlling the evolution of PLs during the training process in ASR. To the best of our knowledge, this is the first study that shows the feasibility of generating PLs from the very start of the training. We are able to achieve this using two techniques that avoid instabilities which lead to degenerate models that do not generalize. Firstly, we control the evolution of PLs through a curriculum that uses the online changes in PLs to control the membership of the cache of PLs and improve generalization. Secondly, we find that by sampling transcriptions from the predictive distribution, rather than only using the best transcription, we can stabilize training further. With these techniques, our ST models match prior works without an external language model.
We introduce FLEURS, the Few-shot Learning Evaluation of Universal Representations of Speech benchmark. FLEURS is an n-way parallel speech dataset in 102 languages built on top of the machine translation FLoRes-101 benchmark, with approximately 12 hours of speech supervision per language. FLEURS can be used for a variety of speech tasks, including Automatic Speech Recognition (ASR), Speech Language Identification (Speech LangID), Translation and Retrieval. In this paper, we provide baselines for the tasks based on multilingual pre-trained models like mSLAM. The goal of FLEURS is to enable speech technology in more languages and catalyze research in low-resource speech understanding.