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

• URL: http://arxiv.org/abs/2410.18363v1
• Date: Thu, 24 Oct 2024 01:58:11 GMT
• Title: Contextual Biasing to Improve Domain-specific Custom Vocabulary Audio Transcription without Explicit Fine-Tuning of Whisper Model
• Authors: Vishakha Lall, Yisi Liu,
• Abstract summary: 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.
• Score: 0.0
• License:
• Abstract: 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 specific vocabularies. Addressing this challenge typically involves fine-tuning the model, which demands extensive labeled audio data that is often difficult to acquire and unavailable for specific domains. In this study, we propose a method to enhance transcription accuracy without explicit fine-tuning or altering model parameters, using a relatively small training dataset. Our method leverages contextual biasing, to direct Whisper model's output towards a specific vocabulary by integrating a neural-symbolic prefix tree structure to guide the model's transcription output. To validate our approach, we conducted experiments using a validation dataset comprising maritime data collected within a simulated training environment. A comparison between the original Whisper models of varying parameter sizes and our biased model revealed a notable reduction in transcription word error rate and enhanced performance of downstream applications. Our findings suggest that this methodology holds promise for improving speech-to-text translation performance in domains characterized by limited vocabularies.

Related papers

• Controlled Randomness Improves the Performance of Transformer Models [4.678970068275123]
  We introduce controlled randomness, i.e. noise, into the training process to improve fine-tuning language models. We find that adding such noise can improve the performance in our two downstream tasks of joint named entity recognition and relation extraction and text summarization.
  arXiv  Detail & Related papers  (2023-10-20T14:12:55Z)
• Optimized Tokenization for Transcribed Error Correction [10.297878672883973]
  We show that the performance of correction models can be significantly increased by training solely using synthetic data. Specifically, we show that synthetic data generated using the error distribution derived from a set of transcribed data outperforms the common approach of applying random perturbations.
  arXiv  Detail & Related papers  (2023-10-16T12:14:21Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition [14.744220870243932]
  We propose to use lightweight character representations to encode fine-grained pronunciation features to improve contextual biasing. We further integrate pretrained neural language model (NLM) based encoders to encode the utterance's semantic context. Experiments using a Conformer Transducer model on the Librispeech dataset show a 4.62% - 9.26% relative WER improvement on different biasing list sizes.
  arXiv  Detail & Related papers  (2023-05-09T08:51:44Z)
• Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization [94.4409074435894]
  We propose a novel and effective fine-tuning framework, named Layerwise Noise Stability Regularization (LNSR) Specifically, we propose to inject the standard Gaussian noise and regularize hidden representations of the fine-tuned model. We demonstrate the advantages of the proposed method over other state-of-the-art algorithms including L2-SP, Mixout and SMART.
  arXiv  Detail & Related papers  (2022-06-12T04:42:49Z)
• Unsupervised Mismatch Localization in Cross-Modal Sequential Data [5.932046800902776]
  We develop an unsupervised learning algorithm that can infer the relationship between content-mismatched cross-modal data. We propose a hierarchical Bayesian deep learning model, named mismatch localization variational autoencoder (ML-VAE), that decomposes the generative process of the speech into hierarchically structured latent variables. Our experimental results show that ML-VAE successfully locates the mismatch between text and speech, without the need for human annotations.
  arXiv  Detail & Related papers  (2022-05-05T14:23:27Z)
• Self-Normalized Importance Sampling for Neural Language Modeling [97.96857871187052]
  In this work, we propose self-normalized importance sampling. Compared to our previous work, the criteria considered in this work are self-normalized and there is no need to further conduct a correction step. We show that our proposed self-normalized importance sampling is competitive in both research-oriented and production-oriented automatic speech recognition tasks.
  arXiv  Detail & Related papers  (2021-11-11T16:57:53Z)
• Factorized Neural Transducer for Efficient Language Model Adaptation [51.81097243306204]
  We propose a novel model, factorized neural Transducer, by factorizing the blank and vocabulary prediction. It is expected that this factorization can transfer the improvement of the standalone language model to the Transducer for speech recognition. We demonstrate that the proposed factorized neural Transducer yields 15% to 20% WER improvements when out-of-domain text data is used for language model adaptation.
  arXiv  Detail & Related papers  (2021-09-27T15:04:00Z)
• SDA: Improving Text Generation with Self Data Augmentation [88.24594090105899]
  We propose to improve the standard maximum likelihood estimation (MLE) paradigm by incorporating a self-imitation-learning phase for automatic data augmentation. Unlike most existing sentence-level augmentation strategies, our method is more general and could be easily adapted to any MLE-based training procedure.
  arXiv  Detail & Related papers  (2021-01-02T01:15:57Z)
• Grounded Compositional Outputs for Adaptive Language Modeling [59.02706635250856]
  A language model's vocabulary$-$typically selected before training and permanently fixed later$-$affects its size. We propose a fully compositional output embedding layer for language models. To our knowledge, the result is the first word-level language model with a size that does not depend on the training vocabulary.
  arXiv  Detail & Related papers  (2020-09-24T07:21:14Z)
• Syntactic Data Augmentation Increases Robustness to Inference Heuristics [27.513414694720716]
  Pretrained neural models such as BERT show high accuracy on standard datasets, but a surprising lack of sensitivity to word order on controlled challenge sets. We explore several methods to augment standard training sets with syntactically informative examples, generated by applying syntactic transformations to sentences from the MNLI corpus. The best-performing augmentation method, subject/object inversion, improved BERT's accuracy on controlled examples that diagnose sensitivity to word order from 0.28 to 0.73, without affecting performance on the MNLI test set.
  arXiv  Detail & Related papers  (2020-04-24T21:35:26Z)

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.