mlsanityData to 14 Oct 2026

Pronunciation-aware unique character encoding for RNN Transducer-based Mandarin speech recognition

arXiv 2207.14578 ↗First posted 29 Jul 2022cs.CL cs.SD eess.AScited by 1

Not on the map. Why?

Abstract (arXiv)

For Mandarin end-to-end (E2E) automatic speech recognition (ASR) tasks, compared to character-based modeling units, pronunciation-based modeling units could improve the sharing of modeling units in model training but meet homophone problems. In this study, we propose to use a novel pronunciation-aware unique character encoding for building E2E RNN-T-based Mandarin ASR systems. The proposed encoding is a combination of pronunciation-base syllable and character index (CI). By introducing the CI, the RNN-T model can overcome the homophone problem while utilizing the pronunciation information for extracting modeling units. With the proposed encoding, the model outputs can be converted into the final recognition result through a one-to-one mapping. We conducted experiments on Aishell and MagicData datasets, and the experimental results showed the effectiveness of the proposed method.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 30 references that are in the map. First posted on arXiv 29 Jul 2022.

Builds on

22 of 30 references.

References · 22

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  5. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  6. 2015Listen, Attend and Spellcited by 543
  7. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 373
  8. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  9. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 235
  10. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
  11. 2020A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latencycited by 100
  12. 2014End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Resultscited by 68
10 more
  1. 2020Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capabilitycited by 63
  2. 2020Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducercited by 22
  3. 2020Simplified Self-Attention for Transformer-based End-to-End Speech Recognitioncited by 20
  4. 2021On Addressing Practical Challenges for RNN-Transducercited by 19
  5. 2020Cascade RNN-Transducer: Syllable Based Streaming On-device Mandarin Speech Recognition with a Syllable-to-Character Convertercited by 16
  6. 2017Building competitive direct acoustics-to-word models for English conversational speech recognitioncited by 10
  7. 2021Language model fusion for streaming end to end speech recognitioncited by 8
  8. 2021Sub-Character Tokenization for Chinese Pretrained Language Modelscited by 7
  9. 2018A comparable study of modeling units for end-to-end Mandarin speech recognitioncited by 5
  10. 2017Subword and Crossword Units for CTC Acoustic Modelscited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Transducers with Pronunciation-aware Embeddings for Automatic Speech Recognitioncited by 0