A Lexical-aware Non-autoregressive Transformer-based ASR Model

• URL: http://arxiv.org/abs/2305.10839v1
• Date: Thu, 18 May 2023 09:50:47 GMT
• Title: A Lexical-aware Non-autoregressive Transformer-based ASR Model
• Authors: Chong-En Lin, Kuan-Yu Chen
• Abstract summary: We propose a lexical-aware non-autoregressive Transformer-based (LA-NAT) ASR framework, which consists of an acoustic encoder, a speech-text shared encoder, and a speech-text shared decoder. LA-NAT aims to make the ASR model aware of lexical information, so the resulting model is expected to achieve better results by leveraging the learned linguistic knowledge.
• Score: 9.500518278458905
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Non-autoregressive automatic speech recognition (ASR) has become a mainstream of ASR modeling because of its fast decoding speed and satisfactory result. To further boost the performance, relaxing the conditional independence assumption and cascading large-scaled pre-trained models are two active research directions. In addition to these strategies, we propose a lexical-aware non-autoregressive Transformer-based (LA-NAT) ASR framework, which consists of an acoustic encoder, a speech-text shared encoder, and a speech-text shared decoder. The acoustic encoder is used to process the input speech features as usual, and the speech-text shared encoder and decoder are designed to train speech and text data simultaneously. By doing so, LA-NAT aims to make the ASR model aware of lexical information, so the resulting model is expected to achieve better results by leveraging the learned linguistic knowledge. A series of experiments are conducted on the AISHELL-1, CSJ, and TEDLIUM 2 datasets. According to the experiments, the proposed LA-NAT can provide superior results than other recently proposed non-autoregressive ASR models. In addition, LA-NAT is a relatively compact model than most non-autoregressive ASR models, and it is about 58 times faster than the classic autoregressive model.

Related papers

• Cross-Speaker Encoding Network for Multi-Talker Speech Recognition [74.97576062152709]
  Cross-MixSpeaker. Network addresses limitations of SIMO models by aggregating cross-speaker representations. Network is integrated with SOT to leverage both the advantages of SIMO and SISO.
  arXiv  Detail & Related papers  (2024-01-08T16:37:45Z)
• Leveraging Pretrained ASR Encoders for Effective and Efficient End-to-End Speech Intent Classification and Slot Filling [13.515248068374625]
  We propose to use an encoder pretrained on speech recognition (ASR) to initialize an end-to-end (E2E) Conformer-Transformer model. Our model achieves the new state-of-the-art results on the SLURP dataset, with 90.14% intent accuracy and 82.27% SLURP-F1.
  arXiv  Detail & Related papers  (2023-07-13T20:50:19Z)
• Joint Encoder-Decoder Self-Supervised Pre-training for ASR [0.0]
  Self-supervised learning has shown tremendous success in various speech-related downstream tasks. In this paper, we propose a new paradigm that exploits the power of a decoder during self-supervised learning.
  arXiv  Detail & Related papers  (2022-06-09T12:45:29Z)
• Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data [145.95460945321253]
  We introduce two pre-training tasks for the encoder-decoder network using acoustic units, i.e., pseudo codes. The proposed Speech2C can relatively reduce the word error rate (WER) by 19.2% over the method without decoder pre-training.
  arXiv  Detail & Related papers  (2022-03-31T15:33:56Z)
• Streaming Multi-Talker ASR with Token-Level Serialized Output Training [53.11450530896623]
  t-SOT is a novel framework for streaming multi-talker automatic speech recognition. The t-SOT model has the advantages of less inference cost and a simpler model architecture. For non-overlapping speech, the t-SOT model is on par with a single-talker ASR model in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2022-02-02T01:27:21Z)
• Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring [83.32560748324667]
  This article describes an efficient end-to-end speech translation (E2E-ST) framework based on non-autoregressive (NAR) models. We propose a unified NAR E2E-ST framework called Orthros, which has an NAR decoder and an auxiliary shallow AR decoder on top of the shared encoder.
  arXiv  Detail & Related papers  (2021-09-09T16:50:16Z)
• Non-autoregressive Transformer-based End-to-end ASR using BERT [13.07939371864781]
  This paper presents a transformer-based end-to-end automatic speech recognition (ASR) model based on BERT. A series of experiments conducted on the AISHELL-1 dataset demonstrates competitive or superior results.
  arXiv  Detail & Related papers  (2021-04-10T16:22:17Z)
• Transformer-based ASR Incorporating Time-reduction Layer and Fine-tuning with Self-Knowledge Distillation [11.52842516726486]
  We propose a Transformer-based ASR model with the time reduction layer, in which we incorporate time reduction layer inside transformer encoder layers. We also introduce a fine-tuning approach for pre-trained ASR models using self-knowledge distillation (S-KD) which further improves the performance of our ASR model. With language model (LM) fusion, we achieve new state-of-the-art word error rate (WER) results for Transformer-based ASR models.
  arXiv  Detail & Related papers  (2021-03-17T21:02:36Z)
• 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)
• 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)
• Streaming automatic speech recognition with the transformer model [59.58318952000571]
  We propose a transformer based end-to-end ASR system for streaming ASR. We apply time-restricted self-attention for the encoder and triggered attention for the encoder-decoder attention mechanism. Our proposed streaming transformer architecture achieves 2.8% and 7.2% WER for the "clean" and "other" test data of LibriSpeech.
  arXiv  Detail & Related papers  (2020-01-08T18:58:02Z)

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.