BayesSpeech: A Bayesian Transformer Network for Automatic Speech Recognition

• URL: http://arxiv.org/abs/2301.11276v1
• Date: Mon, 16 Jan 2023 16:19:04 GMT
• Title: BayesSpeech: A Bayesian Transformer Network for Automatic Speech Recognition
• Authors: Will Rieger
• Abstract summary: Recent developments using End-to-End Deep Learning models have been shown to have near or better performance than state of the art Recurrent Neural Networks (RNNs) on Automatic Speech Recognition tasks. We show how the introduction of variance in the weights leads to faster training time and near state-of-the-art performance on LibriSpeech-960.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent developments using End-to-End Deep Learning models have been shown to have near or better performance than state of the art Recurrent Neural Networks (RNNs) on Automatic Speech Recognition tasks. These models tend to be lighter weight and require less training time than traditional RNN-based approaches. However, these models take frequentist approach to weight training. In theory, network weights are drawn from a latent, intractable probability distribution. We introduce BayesSpeech for end-to-end Automatic Speech Recognition. BayesSpeech is a Bayesian Transformer Network where these intractable posteriors are learned through variational inference and the local reparameterization trick without recurrence. We show how the introduction of variance in the weights leads to faster training time and near state-of-the-art performance on LibriSpeech-960.

Related papers

• Continual Learning for On-Device Speech Recognition using Disentangled Conformers [54.32320258055716]
  We introduce a continual learning benchmark for speaker-specific domain adaptation derived from LibriVox audiobooks. We propose a novel compute-efficient continual learning algorithm called DisentangledCL. Our experiments show that the DisConformer models significantly outperform baselines on general ASR.
  arXiv  Detail & Related papers  (2022-12-02T18:58:51Z)
• Contextual-Utterance Training for Automatic Speech Recognition [65.4571135368178]
  We propose a contextual-utterance training technique which makes use of the previous and future contextual utterances. Also, we propose a dual-mode contextual-utterance training technique for streaming automatic speech recognition (ASR) systems. The proposed technique is able to reduce both the WER and the average last token emission latency by more than 6% and 40ms relative.
  arXiv  Detail & Related papers  (2022-10-27T08:10:44Z)
• Self-supervised Learning with Random-projection Quantizer for Speech Recognition [51.24368930992091]
  We present a simple and effective self-supervised learning approach for speech recognition. The approach learns a model to predict masked speech signals, in the form of discrete labels. It achieves similar word-error-rates as previous work using self-supervised learning with non-streaming models.
  arXiv  Detail & Related papers  (2022-02-03T21:29:04Z)
• Visualising and Explaining Deep Learning Models for Speech Quality Prediction [0.0]
  The non-intrusive speech quality prediction model NISQA is analyzed in this paper. It is composed of a convolutional neural network (CNN) and a recurrent neural network (RNN)
  arXiv  Detail & Related papers  (2021-12-12T12:50:03Z)
• On Addressing Practical Challenges for RNN-Transduce [72.72132048437751]
  We adapt a well-trained RNN-T model to a new domain without collecting the audio data. We obtain word-level confidence scores by utilizing several types of features calculated during decoding. The proposed time stamping method can get less than 50ms word timing difference on average.
  arXiv  Detail & Related papers  (2021-04-27T23:31:43Z)
• DEEPF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals [11.939409227407769]
  We propose a novel pitch estimation technique called DeepF0. It leverages the available annotated data to directly learn from the raw audio in a data-driven manner.
  arXiv  Detail & Related papers  (2021-02-11T23:11:22Z)
• Streaming end-to-end multi-talker speech recognition [34.76106500736099]
  We propose the Streaming Unmixing and Recognition Transducer (SURT) for end-to-end multi-talker speech recognition. Our model employs the Recurrent Neural Network Transducer (RNN-T) as the backbone that can meet various latency constraints. Based on experiments on the publicly available LibriSpeechMix dataset, we show that HEAT can achieve better accuracy compared with PIT.
  arXiv  Detail & Related papers  (2020-11-26T06:28:04Z)
• Pretraining Techniques for Sequence-to-Sequence Voice Conversion [57.65753150356411]
  Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. We propose to transfer knowledge from other speech processing tasks where large-scale corpora are easily available, typically text-to-speech (TTS) and automatic speech recognition (ASR) We argue that VC models with such pretrained ASR or TTS model parameters can generate effective hidden representations for high-fidelity, highly intelligible converted speech.
  arXiv  Detail & Related papers  (2020-08-07T11:02:07Z)
• RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions [73.45995446500312]
  We analyze the generalization properties of streaming and non-streaming recurrent neural network transducer (RNN-T) based end-to-end models. We propose two solutions: combining multiple regularization techniques during training, and using dynamic overlapping inference.
  arXiv  Detail & Related papers  (2020-05-07T06:24:47Z)
• Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks [23.88788382262305]
  temporal convolutional recurrent network (TCRN) is an end-to-end model that directly map noisy waveform to clean waveform. We show that our model is able to improve the performance of model, compared with existing convolutional recurrent networks.
  arXiv  Detail & Related papers  (2020-02-02T04:26:50Z)
• Leveraging End-to-End Speech Recognition with Neural Architecture Search [0.0]
  We show that a large improvement in the accuracy of deep speech models can be achieved with effective Neural Architecture Optimization. Our method achieves test error of 7% Word Error Rate (WER) on the LibriSpeech corpus and 13% Phone Error Rate (PER) on the TIMIT corpus, on par with state-of-the-art results.
  arXiv  Detail & Related papers  (2019-12-11T08:15:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.