Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition

• URL: http://arxiv.org/abs/2101.06699v2
• Date: Sun, 24 Jan 2021 13:27:57 GMT
• Title: Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition
• Authors: Cheng Yi, Shiyu Zhou, Bo Xu
• Abstract summary: 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.
• Score: 9.732767611907068
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic pre-training has already shown its amazing ASR performance, while the transcription is still inadequate for language modeling in end-to-end models. 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. The fused model only needs to learn the transfer from speech to language during fine-tuning on limited labeled data. The length of the two modalities is matched by a monotonic attention mechanism without additional parameters. Besides, a fully connected layer is introduced for the hidden mapping between modalities. We further propose a scheduled fine-tuning strategy to preserve and utilize the text context modeling ability of the pre-trained linguistic encoder. Experiments show our effective utilizing of pre-trained modules. Our model achieves better recognition performance on CALLHOME corpus (15 hours) than other end-to-end models.

Related papers

• Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition [12.77573161345651]
  This paper proposes integrating a pre-trained speech representation model and a large language model (LLM) for E2E ASR. The proposed model enables the optimization of the entire ASR process, including acoustic feature extraction and acoustic and language modeling.
  arXiv  Detail & Related papers  (2023-12-06T18:34:42Z)
• Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization [48.35495352015281]
  End-to-end speech summarization (E2E SSum) directly summarizes input speech into easy-to-read short sentences with a single model. Due to the high cost of collecting speech-summary pairs, an E2E SSum model tends to suffer from training data scarcity and output unnatural sentences. We propose for the first time to integrate a pre-trained language model (LM) into the E2E SSum decoder via transfer learning.
  arXiv  Detail & Related papers  (2023-06-07T08:23:58Z)
• SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training [106.34112664893622]
  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. Our proposed SpeechUT is fine-tuned and evaluated on automatic speech recognition (ASR) and speech translation (ST) tasks.
  arXiv  Detail & Related papers  (2022-10-07T17:57:45Z)
• 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)
• A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition [25.473191378558138]
  We leverage unpaired data to train a general sequence-to-sequence model. Inspired by the complementarity of speech-PseudoLabel pair and SynthesizedAudio-text pair, we propose a complementary joint training(CJT) method.
  arXiv  Detail & Related papers  (2022-04-05T07:02:53Z)
• Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers [13.372686722688325]
  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.
  arXiv  Detail & Related papers  (2022-02-16T07:02:24Z)
• Speech Summarization using Restricted Self-Attention [79.89680891246827]
  We introduce a single model optimized end-to-end for speech summarization. We demonstrate that the proposed model learns to directly summarize speech for the How-2 corpus of instructional videos.
  arXiv  Detail & Related papers  (2021-10-12T18:21:23Z)
• Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining [64.35907499990455]
  We propose a framework to learn semantics directly from speech with semi-supervision from transcribed or untranscribed speech. Our framework is built upon pretrained end-to-end (E2E) ASR and self-supervised language models, such as BERT. In parallel, we identify two essential criteria for evaluating SLU models: environmental noise-robustness and E2E semantics evaluation.
  arXiv  Detail & Related papers  (2020-10-26T18:21:27Z)
• Adapting End-to-End Speech Recognition for Readable Subtitles [15.525314212209562]
  In some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time. We first investigate a cascaded system, where an unsupervised compression model is used to post-edit the transcribed speech. Experiments show that with limited data far less than needed for training a model from scratch, we can adapt a Transformer-based ASR model to incorporate both transcription and compression capabilities.
  arXiv  Detail & Related papers  (2020-05-25T14:42:26Z)
• Deliberation Model Based Two-Pass End-to-End Speech Recognition [52.45841282906516]
  A two-pass model has been proposed to rescore streamed hypotheses using the non-streaming Listen, Attend and Spell (LAS) model. The model attends to acoustics to rescore hypotheses, as opposed to a class of neural correction models that use only first-pass text hypotheses. A bidirectional encoder is used to extract context information from first-pass hypotheses.
  arXiv  Detail & Related papers  (2020-03-17T22:01:12Z)

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.