mlsanityData to 7 Oct 2026

A meta learning scheme for fast accent domain expansion in Mandarin speech recognition

arXiv 2307.12262 ↗First posted 23 Jul 2023cs.SD cs.CL cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

Spoken languages show significant variation across mandarin and accent. Despite the high performance of mandarin automatic speech recognition (ASR), accent ASR is still a challenge task. In this paper, we introduce meta-learning techniques for fast accent domain expansion in mandarin speech recognition, which expands the field of accents without deteriorating the performance of mandarin ASR. Meta-learning or learn-to-learn can learn general relation in multi domains not only for over-fitting a specific domain. So we select meta-learning in the domain expansion task. This more essential learning will cause improved performance on accent domain extension tasks. We combine the methods of meta learning and freeze of model parameters, which makes the recognition performance more stable in different cases and the training faster about 20%. Our approach significantly outperforms other methods about 3% relatively in the accent domain expansion task. Compared to the baseline model, it improves relatively 37% under the condition that the mandarin test set remains unchanged. In addition, it also proved this method to be effective on a large amount of data with a relative performance improvement of 4% on the accent test set.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 22 references that are in the map. First posted on arXiv 23 Jul 2023.

Builds on

20 of 22 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  6. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  7. 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 254
  8. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
  9. 2018Domain Adversarial Training for Accented Speech Recognitioncited by 40
  10. 2021Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speechcited by 30
  11. 2019Meta Learning for End-to-End Low-Resource Speech Recognitioncited by 29
  12. 2020Learning Fast Adaptation on Cross-Accented Speech Recognitioncited by 28
8 more
  1. 2019Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systemscited by 25
  2. 2020REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabelingcited by 18
  3. 2018Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognitioncited by 14
  4. 2021WNARS: WFST based Non-autoregressive Streaming End-to-End Speech Recognitioncited by 10
  5. 2020Multi-Accent Adaptation based on Gate Mechanismcited by 9
  6. 2019Domain Expansion in DNN-based Acoustic Models for Robust Speech Recognitioncited by 6
  7. 2018Advancing Multi-Accented LSTM-CTC Speech Recognition using a Domain Specific Student-Teacher Learning Paradigmcited by 5
  8. 2020Domain Adaptation Using Class Similarity for Robust Speech Recognitioncited by 3

Built on by

Not cited yet.