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

• URL: http://arxiv.org/abs/2506.09448v1
• Date: Wed, 11 Jun 2025 06:53:40 GMT
• Title: OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
• Authors: Yui Sudo, Yusuke Fujita, Atsushi Kojima, Tomoya Mizumoto, Lianbo Liu,
• Abstract summary: This paper integrates an existing contextual biasing (CB) method with Open Whisper-Style Speech Models (OWSM) v3.1 while freezing its pre-trained parameters.<n> Experimental results show that the proposed method improves the biasing word error rate (B-WER) by 11.6 points.
• Score: 8.171886468845049
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Robust Persian Digit Recognition in Noisy Environments Using Hybrid CNN-BiGRU Model [1.5566524830295307]
  This study addresses isolated spoken Persian digit recognition (zero to nine) under noisy conditions.<n>A hybrid model combining residual convolutional neural networks and bidirectional gated units (BiGRU) is proposed.<n> Experimental results demonstrate the model's effectiveness, achieving 98.53%, 96.10%, and 95.92% accuracy on training, validation, and test sets.
  arXiv  Detail & Related papers  (2024-12-14T15:11:42Z)
• CLAIR-A: Leveraging Large Language Models to Judge Audio Captions [73.51087998971418]
  evaluating machine-generated audio captions is a complex task that requires considering diverse factors. We propose CLAIR-A, a simple and flexible method that leverages the zero-shot capabilities of large language models. In our evaluations, CLAIR-A better predicts human judgements of quality compared to traditional metrics.
  arXiv  Detail & Related papers  (2024-09-19T17:59:52Z)
• Speech foundation models on intelligibility prediction for hearing-impaired listeners [4.742307809368852]
  Speech foundation models (SFMs) have been benchmarked on many speech processing tasks. We present a systematic evaluation of 10 SFMs on one such application: Speech intelligibility prediction. We propose a simple method that learns a specialized prediction head on top of frozen SFMs to approach the problem.
  arXiv  Detail & Related papers  (2024-01-24T18:26:52Z)
• Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition [10.62060432965311]
  We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR) Our methodology leverages both acoustic information and external linguistic representations to generate accurate speech transcription contexts.
  arXiv  Detail & Related papers  (2023-10-10T09:04:33Z)
• Contextual-Utterance Training for Automatic Speech Recognition [65.4571135368178]
  We propose a contextual-utterance training technique which makes use of the previous and future contextual utterances. Also, we propose a dual-mode contextual-utterance training technique for streaming automatic speech recognition (ASR) systems. The proposed technique is able to reduce both the WER and the average last token emission latency by more than 6% and 40ms relative.
  arXiv  Detail & Related papers  (2022-10-27T08:10:44Z)
• End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system [61.148549738631814]
  End-to-end (E2E) speech recognition architectures assemble all components of traditional speech recognition system into a single model. Although it simplifies ASR system, it introduces contextual ASR drawback: the E2E model has worse performance on utterances containing infrequent proper nouns. We propose to add a contextual bias attention (CBA) module to attention based encoder decoder (AED) model to improve its ability of recognizing the contextual phrases.
  arXiv  Detail & Related papers  (2022-02-18T03:26:02Z)
• Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction [109.44933866397123]
  Noise robustness is essential for deploying automatic speech recognition systems in real-world environments. We employ a noise-robust representation learned by a refined self-supervised framework for noisy speech recognition. We achieve comparable performance to the best supervised approach reported with only 16% of labeled data.
  arXiv  Detail & Related papers  (2021-10-28T20:39:02Z)
• A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter It [3.18475216176047]
  We design the first method for revealing the identity of the speaker of a training utterance with access only to a gradient. We show that it is possible to reveal the speaker's identity with 34% top-1 accuracy (51% top-5 accuracy) on the LibriSpeech dataset.
  arXiv  Detail & Related papers  (2021-04-15T23:15:12Z)
• MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition [54.84624870942339]
  MixSpeech is a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR) We apply MixSpeech on two popular end-to-end speech recognition models including LAS (Listen, Attend and Spell) and Transformer. Experimental results show that MixSpeech achieves better accuracy than the baseline models without data augmentation.
  arXiv  Detail & Related papers  (2021-02-25T03:40:43Z)
• Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition [64.9317368575585]
  This paper proposes a gated recurrent fusion (GRF) method with joint training framework for robust end-to-end ASR. The GRF algorithm is used to dynamically combine the noisy and enhanced features. The proposed method achieves the relative character error rate (CER) reduction of 10.04% over the conventional joint enhancement and transformer method.
  arXiv  Detail & Related papers  (2020-11-09T08:52:05Z)
• An Effective Contextual Language Modeling Framework for Speech Summarization with Augmented Features [13.97006782398121]
  Bidirectional Representations from Transformers (BERT) model was proposed and has achieved record-breaking success on many natural language processing tasks. We explore the incorporation of confidence scores into sentence representations to see if such an attempt could help alleviate the negative effects caused by imperfect automatic speech recognition. We validate the effectiveness of our proposed method on a benchmark dataset.
  arXiv  Detail & Related papers  (2020-06-01T18:27:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.