mlsanityData to 7 Oct 2026

Decoupling recognition and transcription in Mandarin ASR

arXiv 2108.01129 ↗First posted 2 Aug 2021cs.CL cs.SD eess.AScited by 6

Not on the map. Why?

Abstract (arXiv)

Much of the recent literature on automatic speech recognition (ASR) is taking an end-to-end approach. Unlike English where the writing system is closely related to sound, Chinese characters (Hanzi) represent meaning, not sound. We propose factoring audio -> Hanzi into two sub-tasks: (1) audio -> Pinyin and (2) Pinyin -> Hanzi, where Pinyin is a system of phonetic transcription of standard Chinese. Factoring the audio -> Hanzi task in this way achieves 3.9% CER (character error rate) on the Aishell-1 corpus, the best result reported on this dataset so far.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 39 of its 53 references that are in the map. First posted on arXiv 2 Aug 2021.

Builds on

39 of 53 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 364
  5. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
  6. 2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 95
  7. 2021Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictionscited by 61
  8. 2018Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytescited by 54
  9. 2021FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognitioncited by 43
  10. 2020Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognitioncited by 37
  11. 2021Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognitioncited by 33
  12. 2020Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languagescited by 30
27 more
  1. 2020Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognitioncited by 24
  2. 2020Non-Autoregressive Transformer ASR with CTC-Enhanced Decoder Inputcited by 24
  3. 2020Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognitioncited by 22
  4. 2020Simplified Self-Attention for Transformer-based End-to-End Speech Recognitioncited by 20
  5. 2020Cascade RNN-Transducer: Syllable Based Streaming On-device Mandarin Speech Recognition with a Syllable-to-Character Convertercited by 16
  6. 2021Non-autoregressive Transformer-based End-to-end ASR using BERTcited by 13
  7. 2021Efficient conformer-based speech recognition with linear attentioncited by 13
  8. 2020A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognitioncited by 12
  9. 2021Boundary and Context Aware Training for CIF-based Non-Autoregressive End-to-end ASRcited by 12
  10. 2018A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinesecited by 10
  11. 2021Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASRcited by 10
  12. 2021WNARS: WFST based Non-autoregressive Streaming End-to-End Speech Recognitioncited by 10
  13. 2020Transformer with Bidirectional Decoder for Speech Recognitioncited by 7
  14. 2020Decoupling Pronunciation and Language for End-to-end Code-switching Automatic Speech Recognitioncited by 7
  15. 2020Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognitioncited by 7
  16. 2020Multi-head Monotonic Chunkwise Attention For Online Speech Recognitioncited by 5
  17. 2020Transformer-based Online Speech Recognition with Decoder-end Adaptive Computation Stepscited by 5
  18. 2021Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognitioncited by 5
  19. 2021Head-synchronous Decoding for Transformer-based Streaming ASRcited by 5
  20. 2020One In A Hundred: Select The Best Predicted Sequence from Numerous Candidates for Streaming Speech Recognitioncited by 4
  21. 2021Transformer-based end-to-end speech recognition with residual Gaussian-based self-attentioncited by 4
  22. 2021Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Searchcited by 4
  23. 2019Independent language modeling architecture for end-to-end ASRcited by 3
  24. 2020Self-and-Mixed Attention Decoder with Deep Acoustic Structure for Transformer-based LVCSRcited by 3
  25. 2020Multi-QuartzNet: Multi-Resolution Convolution for Speech Recognition with Multi-Layer Feature Fusioncited by 3
  26. 2020Research on Modeling Units of Transformer Transducer for Mandarin Speech Recognitioncited by 2
  27. 2020Improving RNN transducer with normalized jointer networkcited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 1; 2024: 3.

6 papers.

  1. 2023Regeneration Learning: A Learning Paradigm for Data Generationcited by 8
  2. 2024Large Language Model Should Understand Pinyin for Chinese ASR Error Correctioncited by 3
  3. 2021SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognitioncited by 1
  4. 2024Romanization Encoding For Multilingual ASRcited by 1
  5. 2022Multi-Level Modeling Units for End-to-End Mandarin Speech Recognitioncited by 0
  6. 2024Transducers with Pronunciation-aware Embeddings for Automatic Speech Recognitioncited by 0