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

• URL: http://arxiv.org/abs/2309.09552v4
• Date: Thu, 6 Jun 2024 05:18:10 GMT
• Title: A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting
• Authors: Yuang Li, Min Zhang, Chang Su, Yinglu Li, Xiaosong Qiao, Mengxin Ren, Miaomiao Ma, Daimeng Wei, Shimin Tao, Hao Yang,
• Abstract summary: We introduce keyword spotting enhanced Whisper (KWS-Whisper) to recognize user-defined named entities. To optimize the model, we propose a multitask training approach that learns OV-KWS and contextual-ASR tasks. We demonstrate that the OV-KWS can be a plug-and-play module to enhance the ASR error correction methods and frozen Whisper models.
• Score: 14.713947276478647
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Noise-Agnostic Multitask Whisper Training for Reducing False Alarm Errors in Call-for-Help Detection [0.0]
  We propose a novel multitask learning approach that integrates a noise classification head into the ASR encoder. Our method enhances the model's robustness to noisy environments, leading to a significant reduction in false alarms and improved overall call-for-help performance.
  arXiv  Detail & Related papers  (2025-01-20T18:01:42Z)
• Keyword-Guided Adaptation of Automatic Speech Recognition [17.011087631073863]
  We propose a novel approach for improved jargon word recognition by contextual biasing Whisper-based models. We employ a keyword spotting model that leverages the Whisper encoder representation to dynamically generate prompts for guiding the decoder during the transcription process. Our results show a significant improvement in the recognition accuracy of specified keywords and in reducing the overall word error rates.
  arXiv  Detail & Related papers  (2024-06-04T14:20:38Z)
• Continuously Learning New Words in Automatic Speech Recognition [56.972851337263755]
  We propose a self-supervised continual learning approach for Automatic Speech Recognition. We use a memory-enhanced ASR model from the literature to decode new words from the slides. We show that with this approach, we obtain increasing performance on the new words when they occur more frequently.
  arXiv  Detail & Related papers  (2024-01-09T10:39:17Z)
• Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoring [4.819085609772069]
  We propose a novel approach for enhancing contextual recognition within ASR systems via semantic lattice processing. Our solution consists of using Hidden Markov Models and Gaussian Mixture Models (HMM-GMM) along with Deep Neural Networks (DNN) models for better accuracy. We demonstrate the effectiveness of our proposed framework on the LibriSpeech dataset with empirical analyses.
  arXiv  Detail & Related papers  (2023-10-14T23:16:05Z)
• Open-vocabulary Keyword-spotting with Adaptive Instance Normalization [18.250276540068047]
  We propose AdaKWS, a novel method for keyword spotting in which a text encoder is trained to output keyword-conditioned normalization parameters. We show significant improvements over recent keyword spotting and ASR baselines.
  arXiv  Detail & Related papers  (2023-09-13T13:49:42Z)
• Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization [61.60501633397704]
  We investigate the emergent abilities of the recently proposed web-scale speech model Whisper, by adapting it to unseen tasks with prompt engineering. We design task-specific prompts, by either leveraging another large-scale model, or simply manipulating the special tokens in the default prompts. Experiments show that our proposed prompts improve performance by 10% to 45% on the three zero-shot tasks, and even outperform SotA supervised models on some datasets.
  arXiv  Detail & Related papers  (2023-05-18T16:32:58Z)
• Bridging Speech and Textual Pre-trained Models with Unsupervised ASR [70.61449720963235]
  This work proposes a simple yet efficient unsupervised paradigm that connects speech and textual pre-trained models. We show that unsupervised automatic speech recognition (ASR) can improve the representations from speech self-supervised models. Notably, on spoken question answering, we reach the state-of-the-art result over the challenging NMSQA benchmark.
  arXiv  Detail & Related papers  (2022-11-06T04:50:37Z)
• Short-Term Word-Learning in a Dynamically Changing Environment [63.025297637716534]
  We show how to supplement an end-to-end ASR system with a word/phrase memory and a mechanism to access this memory to recognize the words and phrases correctly. We demonstrate significant improvements in the detection rate of new words with only a minor increase in false alarms.
  arXiv  Detail & Related papers  (2022-03-29T10:05:39Z)
• A Comparison of Methods for OOV-word Recognition on a New Public Dataset [0.0]
  We propose using the CommonVoice dataset to create test sets for languages with a high out-of-vocabulary ratio. We then evaluate, within the context of a hybrid ASR system, how much better subword models are at recognizing OOVs. We propose a new method for modifying a subword-based language model so as to better recognize OOV-words.
  arXiv  Detail & Related papers  (2021-07-16T19:39:30Z)
• Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition [62.997667081978825]
  We present an end-to-end ASR system with a word/phrase memory and a mechanism to access this memory to recognize the words and phrases correctly. In this paper we demonstrate that through this mechanism our system is able to recognize more than 85% of newly added words that it previously failed to recognize.
  arXiv  Detail & Related papers  (2021-07-05T21:08:34Z)
• Speech Enhancement for Wake-Up-Word detection in Voice Assistants [60.103753056973815]
  Keywords spotting and in particular Wake-Up-Word (WUW) detection is a very important task for voice assistants. This paper proposes a Speech Enhancement model adapted to the task of WUW detection. It aims at increasing the recognition rate and reducing the false alarms in the presence of these types of noises.
  arXiv  Detail & Related papers  (2021-01-29T18:44:05Z)

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.