2023 INTERSPEECH INTERSPEECH 2023

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

Abstract

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 content words that occur in a particular task may still exhibit poor ASR performance, with contextual biasing a possible remedy. This paper investigates the effectiveness of neural contextual biasing for Whisper combined with GPT-2. Specifically, this paper proposes integrating an adapted tree-constrained pointer generator (TCPGen) component for Whisper and a dedicated training scheme to dynamically adjust the final output without modifying any Whisper model parameters. Experiments across three datasets show a considerable reduction in errors on biasing words with a biasing list of 1000 words. Contextual biasing was more effective when applied to domain-specific data and can boost the performance of Whisper and GPT-2 without losing their generality.

The Questioner
🌉 Interdisciplinary Bridge — Machine Learning and Natural Language Processing and Speech & Audio
🧭 Keyword Pioneer — pointer generator
🐣 Hot Topic Early Bird — large language models
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Speech & Audio