mlsanityData to 7 Oct 2026

OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary

arXiv 2506.09448 ↗First posted 11 Jun 2025cs.SD cs.CL eess.AScited by 4

Not on the map. Why?

Abstract (arXiv)

Speech foundation models (SFMs), such as Open Whisper-Style Speech Models (OWSM), are trained on massive datasets to achieve accurate automatic speech recognition. However, even SFMs struggle to accurately recognize rare and unseen words. While contextual biasing (CB) is a promising approach to improve recognition of such words, most CB methods are trained from scratch, resulting in lower performance than SFMs due to the lack of pre-trained knowledge. This paper integrates an existing CB method with OWSM v3.1 while freezing its pre-trained parameters. By leveraging the knowledge embedded in SFMs, the proposed method enables effective CB while preserving the advantages of SFMs, even with a small dataset. Experimental results show that the proposed method improves the biasing word error rate (B-WER) by 11.6 points, resulting in a 0.9 point improvement in the overall WER while reducing the real-time factor by 7.5% compared to the non-biasing baseline on the LibriSpeech 100 test-clean set.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 32 of its 41 references that are in the map. First posted on arXiv 11 Jun 2025.

Builds on

32 of 41 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 591
  5. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  6. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 492
  7. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  8. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languagescited by 228
  9. 2018Deep context: end-to-end contextual speech recognitioncited by 136
  10. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  11. 2022E-Branchformer: Branchformer with Enhanced merging for speech recognitioncited by 90
  12. 2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 86
20 more
  1. 2020Contextual RNN-T For Open Domain ASRcited by 85
  2. 2024OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformercited by 74
  3. 2024OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identificationcited by 34
  4. 2023Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Networkcited by 31
  5. 2021Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognitioncited by 30
  6. 2023Can Contextual Biasing Remain Effective with Whisper and GPT-2?cited by 21
  7. 2024Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Searchcited by 19
  8. 2023PromptASR for contextualized ASR with controllable stylecited by 18
  9. 2023CopyNE: Better Contextual ASR by Copying Named Entitiescited by 13
  10. 2023Phoneme-aware Encoding for Prefix-tree-based Contextual ASRcited by 13
  11. 2024Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Losscited by 9
  12. 2024Contextualized Automatic Speech Recognition with Dynamic Vocabularycited by 8
  13. 2023Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducercited by 6
  14. 2024VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuningcited by 6
  15. 2023Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimationcited by 5
  16. 2023A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spottingcited by 5
  17. 2024InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictionscited by 5
  18. 2024Contextual Biasing to Improve Domain-specific Custom Vocabulary Audio Transcription without Explicit Fine-Tuning of Whisper Modelcited by 5
  19. 2024Joint Beam Search Integrating CTC, Attention, and Transducer Decoderscited by 4
  20. 2023Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognitioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

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

4 papers.

  1. 2026ViMedCSS: A Vietnamese Medical Code-Switching Speech Dataset & Benchmarkcited by 3
  2. 2026When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASRcited by 1
  3. 2026How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMscited by 1
  4. 2025Context Biasing for Pronunciation-Orthography Mismatch in Automatic Speech Recognitioncited by 0