mlsanityData to 14 Oct 2026

Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducer

arXiv 2311.08966 ↗First posted 15 Nov 2023cs.CL cs.SD eess.AScited by 6

Not on the map. Why?

Abstract (arXiv)

Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR). However, deep biasing with large-scale rare words remains challenging, as the performance drops significantly when more distractors exist and there are words with similar grapheme sequences in the bias list. In this paper, we combine the phoneme and textual information of rare words in Transducers to distinguish words with similar pronunciation or spelling. Moreover, the introduction of training with text-only data containing more rare words benefits large-scale deep biasing. The experiments on the LibriSpeech corpus demonstrate that the proposed method achieves state-of-the-art performance on rare word error rate for different scales and levels of bias lists.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 33 of its 46 references that are in the map. First posted on arXiv 15 Nov 2023.

Builds on

33 of 46 references.

References · 33

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  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. 2015Attention-Based Models for Speech Recognitioncited by 401
  6. 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 211
  7. 2019BPE-Dropout: Simple and Effective Subword Regularizationcited by 195
  8. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
  9. 2018Deep context: end-to-end contextual speech recognitioncited by 137
  10. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 101
  11. 2020A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latencycited by 100
  12. 2020Contextual RNN-T For Open Domain ASRcited by 85
21 more
  1. 2022MAESTRO: Matched Speech Text Representations through Modality Matchingcited by 79
  2. 2017Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Modelscited by 68
  3. 2020Deep Shallow Fusion for RNN-T Personalizationcited by 64
  4. 2020On the Comparison of Popular End-to-End Models for Large Scale Speech Recognitioncited by 63
  5. 2020Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capabilitycited by 63
  6. 2022Contextual Adapters for Personalized Speech Recognition in Neural Transducerscited by 57
  7. 2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
  8. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  9. 2023Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Networkcited by 31
  10. 2020Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpuscited by 24
  11. 2022JOIST: A Joint Speech and Text Streaming Model For ASRcited by 24
  12. 2020CIF-based Collaborative Decoding for End-to-end Contextual Speech Recognitioncited by 21
  13. 2022Integrating Text Inputs For Training and Adapting RNN Transducer ASR Modelscited by 20
  14. 2023Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognitioncited by 18
  15. 2018Advancing Acoustic-to-Word CTC Modelcited by 15
  16. 2022Improving Rare Word Recognition with LM-aware MWER Trainingcited by 12
  17. 2022Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognitioncited by 10
  18. 2021Lookup-Table Recurrent Language Models for Long Tail Speech Recognitioncited by 9
  19. 2023JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognitioncited by 9
  20. 2019Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentationcited by 7
  21. 2023Text-only Domain Adaptation using Unified Speech-Text Representation in Transducercited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 1.

6 papers.

  1. 2024Contextualized Automatic Speech Recognition with Dynamic Vocabularycited by 8
  2. 2025OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabularycited by 4
  3. 2024An efficient text augmentation approach for contextualized Mandarin speech recognitioncited by 2
  4. 2025DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognitioncited by 2
  5. 2025Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activationcited by 1
  6. 2026PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMscited by 0