Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning

• URL: http://arxiv.org/abs/2307.10274v2
• Date: Fri, 6 Oct 2023 03:41:30 GMT
• Title: Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning
• Authors: Feng-Ting Liao, Yung-Chieh Chan, Yi-Chang Chen, Chan-Jan Hsu, Da-shan Shiu
• Abstract summary: We show that our model can gain a Word Error Rate (WER) reduction of up to 33% on unseen datasets from various domains. We extend our method to text-only fine-tuning to achieve domain sensitivity as well as domain adaptation.
• Score: 11.585880477614495
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we propose a method to create domain-sensitive speech recognition models that utilize textual domain information by conditioning its generation on a given text prompt. This is accomplished by fine-tuning a pre-trained, end-to-end model (Whisper) to learn from demonstrations with prompt examples. We show that this ability can be generalized to different domains and even various prompt contexts, with our model gaining a Word Error Rate (WER) reduction of up to 33% on unseen datasets from various domains, such as medical conversation, air traffic control communication, and financial meetings. Considering the limited availability of audio-transcript pair data, we further extend our method to text-only fine-tuning to achieve domain sensitivity as well as domain adaptation. We demonstrate that our text-only fine-tuned model can also attend to various prompt contexts, with the model reaching the most WER reduction of 29% on the medical conversation dataset.

Related papers

• Contextual Biasing to Improve Domain-specific Custom Vocabulary Audio Transcription without Explicit Fine-Tuning of Whisper Model [0.0]
  OpenAI's Whisper Automated Speech Recognition model excels in generalizing across diverse datasets and domains. We propose a method to enhance transcription accuracy without explicit fine-tuning or altering model parameters.
  arXiv  Detail & Related papers  (2024-10-24T01:58:11Z)
• Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition [48.527630771422935]
  We propose a synthetic data generation pipeline for multi-speaker conversational ASR. We conduct evaluation by fine-tuning the Whisper ASR model for telephone and distant conversational speech settings.
  arXiv  Detail & Related papers  (2024-08-17T14:47:05Z)
• Language Guided Domain Generalized Medical Image Segmentation [68.93124785575739]
  Single source domain generalization holds promise for more reliable and consistent image segmentation across real-world clinical settings. We propose an approach that explicitly leverages textual information by incorporating a contrastive learning mechanism guided by the text encoder features. Our approach achieves favorable performance against existing methods in literature.
  arXiv  Detail & Related papers  (2024-04-01T17:48:15Z)
• Few-Shot Spoken Language Understanding via Joint Speech-Text Models [18.193191170754744]
  Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations. We leverage such shared representations to address the persistent challenge of limited data availability in spoken language understanding tasks. By employing a pre-trained speech-text model, we find that models fine-tuned on text can be effectively transferred to speech testing data.
  arXiv  Detail & Related papers  (2023-10-09T17:59:21Z)
• Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation [67.98338382984556]
  Mapping two modalities, speech and text, into a shared representation space, is a research topic of using text-only data to improve end-to-end automatic speech recognition (ASR) performance in new domains. In this paper, we proposed novel representations match strategy through down-sampling acoustic representation to align with text modality. Our ASR model can learn unified representations from both modalities better, allowing for domain adaptation using text-only data of the target domain.
  arXiv  Detail & Related papers  (2023-09-04T08:52:59Z)
• Unsupervised Improvement of Audio-Text Cross-Modal Representations [19.960695758478153]
  We study unsupervised approaches to improve the learning framework of such representations with unpaired text and audio. We show that when domain-specific curation is used in conjunction with a soft-labeled contrastive loss, we are able to obtain significant improvement in terms of zero-shot classification performance.
  arXiv  Detail & Related papers  (2023-05-03T02:30:46Z)
• VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning [119.49605266839053]
  We propose a unified cross-modal representation learning framework VATLM (Visual-Audio-Text Language Model) The proposed VATLM employs a unified backbone network to model the modality-independent information. In order to integrate these three modalities into one shared semantic space, VATLM is optimized with a masked prediction task of unified tokens.
  arXiv  Detail & Related papers  (2022-11-21T09:10:10Z)
• A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data [1.14219428942199]
  We propose a simple baseline technique for domain adaptation in end-to-end speech recognition models. We convert the text-only corpus to audio data using single speaker Text to Speech (TTS) engine. We show that single speaker synthetic TTS data coupled with final dense layer only fine-tuning provides reasonable improvements in word error rates.
  arXiv  Detail & Related papers  (2022-06-22T12:07:38Z)
• WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models [57.557319372969495]
  Large-scale auto-regressive language models pretrained on massive text have demonstrated their impressive ability to perform new natural language tasks. Recent studies further show that such a few-shot learning ability can be extended to the text-image setting by training an encoder to encode the images into embeddings. We propose a novel speech understanding framework, WavPrompt, where we finetune a wav2vec model to generate a sequence of audio embeddings understood by the language model.
  arXiv  Detail & Related papers  (2022-03-29T19:08:55Z)
• SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding [61.02342238771685]
  Spoken language understanding requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. Various pre-training methods have been proposed to learn rich representations from large-scale unannotated speech and text. We propose a novel semi-supervised learning framework, SPLAT, to jointly pre-train the speech and language modules.
  arXiv  Detail & Related papers  (2020-10-05T19:29:49Z)

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.