mlsanityData to 7 Oct 2026

SememeASR: Boosting Performance of End-to-End Speech Recognition against Domain and Long-Tailed Data Shift with Sememe Semantic Knowledge

arXiv 2309.01437 ↗First posted 4 Sep 2023cs.SD cs.CL eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, excellent progress has been made in speech recognition. However, pure data-driven approaches have struggled to solve the problem in domain-mismatch and long-tailed data. Considering that knowledge-driven approaches can help data-driven approaches alleviate their flaws, we introduce sememe-based semantic knowledge information to speech recognition (SememeASR). Sememe, according to the linguistic definition, is the minimum semantic unit in a language and is able to represent the implicit semantic information behind each word very well. Our experiments show that the introduction of sememe information can improve the effectiveness of speech recognition. In addition, our further experiments show that sememe knowledge can improve the model's recognition of long-tailed data and enhance the model's domain generalization ability.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 24 references that are in the map. First posted on arXiv 4 Sep 2023.

Builds on

18 of 24 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  4. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  5. 2015Listen, Attend and Spellcited by 542
  6. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 364
  7. 2021WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognitioncited by 189
  8. 2018AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scalecited by 125
  9. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
  10. 2022Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understandingcited by 90
  11. 2014End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Resultscited by 68
  12. 2021Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERTcited by 31
6 more
  1. 2020Simplified Self-Attention for Transformer-based End-to-End Speech Recognitioncited by 20
  2. 2020Multitask Training with Text Data for End-to-End Speech Recognitioncited by 19
  3. 2018Exploring RNN-Transducer for Chinese Speech Recognitioncited by 8
  4. 2018Language Modeling with Sparse Product of Sememe Expertscited by 6
  5. 2022Improving Mandarin Speech Recogntion with Block-augmented Transformercited by 6
  6. 2022Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognitioncited by 5

Built on by

Not cited yet.