paper-with-me

Papers

A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting

2023-09-18 · Yuang Li, Min Zhang, Chang Su, Yinglu Li, Xiaosong Qiao, Mengxin Ren, Miaomiao Ma, Daimeng Wei, Shimin Tao, Hao Yang

The recognition of rare named entities, such as personal names and terminologies, is challenging for automatic speech recognition (ASR) systems, especially when they are not frequently observed in the training data. In this paper, we introduce keyword spotting enhanced Whisper (KWS-Whisper), a novel ASR system that leverages the Whisper model and performs open-vocabulary keyword spotting (OV-KWS) on the hidden states of the Whisper encoder to recognize user-defined named entities. These entities serve as prompts for the Whisper decoder. To optimize the model, we propose a multitask training approach that learns OV-KWS and contextual-ASR tasks. We evaluate our approach on Chinese Aishell hot word subsets and two internal code-switching test sets and show that it significantly improves the entity recall compared to the original Whisper model. Moreover, we demonstrate that the OV-KWS can be a plug-and-play module to enhance the ASR error correction methods and frozen Whisper models.

📄 PDF Abstract BibTeX arXiv:2309.09552

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderHallucinationKeyword Spottingspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Can Contextual Biasing Remain Effective with Whisper and GPT-2?

2023-06-02 · Guangzhi Sun, Xianrui Zheng, Chao Zhang, Philip C. Woodland

End-to-end automatic speech recognition (ASR) and large language models, such as Whisper and GPT-2, have recently been scaled to use vast amounts of training data. Despite the large amount of training data, infrequent co…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Contextual Biasing to Improve Domain-specific Custom Vocabulary Audio Transcription without Explicit Fine-Tuning of Whisper Model

2024-10-24 · Vishakha Lall, Yisi Liu

OpenAI's Whisper Automated Speech Recognition model excels in generalizing across diverse datasets and domains. However, this broad adaptability can lead to diminished performance in tasks requiring recognition of specif…

speech-recognitionSpeech RecognitionSpeech-to-TextSpeech-to-Text Translation

Improving Rare-Word Recognition of Whisper in Zero-Shot Settings

2025-02-17 · Yash Jogi, Vaibhav Aggarwal, Shabari S Nair, Yash Verma 외

Whisper, despite being trained on 680K hours of web-scaled audio data, faces difficulty in recognising rare words like domain-specific terms, with a solution being contextual biasing through prompting. To improve upon th…

Improving Synthetic Data Training for Contextual Biasing Models with a Keyword-Aware Cost Function

2025-09-11 · Chin Yuen Kwok, Jia Qi Yip, Eng Siong Chng arxiv

Rare word recognition can be improved by adapting ASR models to synthetic data that includes these words. Further improvements can be achieved through contextual biasing, which trains and adds a biasing module into the m…

Binary Classification

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

2025-06-11 · Yui Sudo, Yusuke Fujita, Atsushi Kojima, Tomoya Mizumoto 외

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…

Automatic Speech Recognitionspeech-recognitionSpeech Recognition