mlsanityData to 14 Oct 2026

Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimation

arXiv 2305.17846 ↗First posted 29 May 2023cs.SD cs.CL eess.AScited by 5

Not on the map. Why?

Abstract (arXiv)

End-to-end automatic speech recognition (E2E-ASR) has the potential to improve performance, but a specific issue that needs to be addressed is the difficulty it has in handling enharmonic words: named entities (NEs) with the same pronunciation and part of speech that are spelled differently. This often occurs with Japanese personal names that have the same pronunciation but different Kanji characters. Since such NE words tend to be important keywords, ASR easily loses user trust if it misrecognizes them. To solve these problems, this paper proposes a novel retraining-free customized method for E2E-ASRs based on a named-entity-aware E2E-ASR model and phoneme similarity estimation. Experimental results show that the proposed method improves the target NE character error rate by 35.7% on average relative to the conventional E2E-ASR model when selecting personal names as a target NE.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 21 of its 41 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

21 of 41 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Layer Normalizationcited by 5,669
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  4. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  5. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  6. 2015Listen, Attend and Spellcited by 543
  7. 2015Attention-Based Models for Speech Recognitioncited by 401
  8. 2018Deep context: end-to-end contextual speech recognitioncited by 137
  9. 2020Recent Developments on ESPnet Toolkit Boosted by Conformercited by 132
  10. 2017An analysis of incorporating an external language model into a sequence-to-sequence modelcited by 111
  11. 2017Cold Fusion: Training Seq2Seq Models Together with Language Modelscited by 88
  12. 2020Contextual RNN-T For Open Domain ASRcited by 85
9 more
  1. 2022Contextual Adapters for Personalized Speech Recognition in Neural Transducerscited by 57
  2. 2020Class LM and word mapping for contextual biasing in End-to-End ASRcited by 42
  3. 2019Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entitiescited by 41
  4. 2020Using Synthetic Audio to Improve The Recognition of Out-Of-Vocabulary Words in End-To-End ASR Systemscited by 41
  5. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  6. 2021Factorized Neural Transducer for Efficient Language Model Adaptationcited by 32
  7. 2017Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognitioncited by 29
  8. 2021Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Networkcited by 19
  9. 2021A Comparative Study on Neural Architectures and Training Methods for Japanese Speech Recognitioncited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 1.

5 papers.

  1. 2024Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Searchcited by 19
  2. 2024Contextualized Automatic Speech Recognition with Dynamic Vocabularycited by 8
  3. 2025OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabularycited by 4
  4. 2025DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognitioncited by 2
  5. 2026Ruby-ASR: Evidence-Preserving Supervision for Joint Orthographic and Lexical-Reading Recognitioncited by 0