Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers

• URL: http://arxiv.org/abs/2202.07894v1
• Date: Wed, 16 Feb 2022 07:02:24 GMT
• Title: Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers
• Authors: Yotaro Kubo, Shigeki Karita, Michiel Bacchiani
• Abstract summary: Training of end-to-end speech recognizers always requires transcribed utterances. This paper proposes a method for alleviating this issue by transferring knowledge from a language model neural network that can be pretrained with text-only data.
• Score: 13.372686722688325
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of end-to-end speech recognizers always requires transcribed utterances. Since end-to-end models are also known to be severely data hungry, this constraint is crucial especially because obtaining transcribed utterances is costly and can possibly be impractical or impossible. This paper proposes a method for alleviating this issue by transferring knowledge from a language model neural network that can be pretrained with text-only data. Specifically, this paper attempts to transfer semantic knowledge acquired in embedding vectors of large-scale language models. Since embedding vectors can be assumed as implicit representations of linguistic information such as part-of-speech, intent, and so on, those are also expected to be useful modeling cues for ASR decoders. This paper extends two types of ASR decoders, attention-based decoders and neural transducers, by modifying training loss functions to include embedding prediction terms. The proposed systems were shown to be effective for error rate reduction without incurring extra computational costs in the decoding phase.

Related papers

• Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition [110.8431434620642]
  We introduce the generative speech transcription error correction (GenSEC) challenge. This challenge comprises three post-ASR language modeling tasks: (i) post-ASR transcription correction, (ii) speaker tagging, and (iii) emotion recognition. We discuss insights from baseline evaluations, as well as lessons learned for designing future evaluations.
  arXiv  Detail & Related papers  (2024-09-15T16:32:49Z)
• Leveraging Language ID to Calculate Intermediate CTC Loss for Enhanced Code-Switching Speech Recognition [5.3545957730615905]
  We introduce language identification information into the middle layer of the ASR model's encoder. We aim to generate acoustic features that imply language distinctions in a more implicit way, reducing the model's confusion when dealing with language switching.
  arXiv  Detail & Related papers  (2023-12-15T07:46:35Z)
• Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages [58.43299730989809]
  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. This process stands on its own, or can be applied as low-cost second-stage pre-training.
  arXiv  Detail & Related papers  (2022-05-02T17:59:02Z)
• Speech recognition for air traffic control via feature learning and end-to-end training [8.755785876395363]
  We propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block, recurrent neural network (RNN), and connectionist temporal classification loss. Thanks to the ability to learn representations from raw waveforms, the proposed model can be optimized in a complete end-to-end manner.
  arXiv  Detail & Related papers  (2021-11-04T06:38:21Z)
• Lexically Aware Semi-Supervised Learning for OCR Post-Correction [90.54336622024299]
  Much of the existing linguistic data in many languages of the world is locked away in non-digitized books and documents. Previous work has demonstrated the utility of neural post-correction methods on recognition of less-well-resourced languages. We present a semi-supervised learning method that makes it possible to utilize raw images to improve performance.
  arXiv  Detail & Related papers  (2021-11-04T04:39:02Z)
• Factorized Neural Transducer for Efficient Language Model Adaptation [51.81097243306204]
  We propose a novel model, factorized neural Transducer, by factorizing the blank and vocabulary prediction. It is expected that this factorization can transfer the improvement of the standalone language model to the Transducer for speech recognition. We demonstrate that the proposed factorized neural Transducer yields 15% to 20% WER improvements when out-of-domain text data is used for language model adaptation.
  arXiv  Detail & Related papers  (2021-09-27T15:04:00Z)
• Fast End-to-End Speech Recognition via a Non-Autoregressive Model and Cross-Modal Knowledge Transferring from BERT [72.93855288283059]
  We propose a non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once) The model consists of an encoder, a decoder, and a position dependent summarizer (PDS)
  arXiv  Detail & Related papers  (2021-02-15T15:18:59Z)
• Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition [9.732767611907068]
  In this work, we fuse a pre-trained acoustic encoder (wav2vec2.0) and a pre-trained linguistic encoder (BERT) into an end-to-end ASR model. Our model achieves better recognition performance on CALLHOME corpus (15 hours) than other end-to-end models.
  arXiv  Detail & Related papers  (2021-01-17T16:12:44Z)
• A review of on-device fully neural end-to-end automatic speech recognition algorithms [20.469868150587075]
  We review various end-to-end automatic speech recognition algorithms and their optimization techniques for on-device applications. fully neural network end-to-end speech recognition algorithms have been proposed. We extensively discuss their structures, performance, and advantages compared to conventional algorithms.
  arXiv  Detail & Related papers  (2020-12-14T22:18:08Z)
• 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)
• End-to-end speech-to-dialog-act recognition [38.58540444573232]
  We present an end-to-end model which directly converts speech into dialog acts without the deterministic transcription process. In the proposed model, the dialog act recognition network is conjunct with an acoustic-to-word ASR model at its latent layer. The entire network is fine-tuned in an end-to-end manner.
  arXiv  Detail & Related papers  (2020-04-23T18:44:27Z)

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.