WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasing

TL;DR

This paper introduces a retraining-free biasing method for CTC-based speech recognition that enhances the recognition of rare and unknown words by using wildcard CTC for keyword spotting and inter-layer biasing during inference.

Contribution

It presents a novel inference-time biasing technique using wildcard CTC and inter-layer biasing, eliminating the need for retraining and improving recognition of rare words.

Findings

Achieved a 29% improvement in F1 score for unknown words in Japanese speech recognition.

Demonstrated effectiveness without additional training or TTS systems.

Applicable to large-scale models due to no retraining requirement.

Abstract

Despite recent advances in end-to-end speech recognition methods, the output tends to be biased to the training data's vocabulary, resulting in inaccurate recognition of proper nouns and other unknown terms. To address this issue, we propose a method to improve recognition accuracy of such rare words in CTC-based models without additional training or text-to-speech systems. Specifically, keyword spotting is performed using acoustic features of intermediate layers during inference, and a bias is applied to the subsequent layers of the acoustic model for detected keywords. For keyword detection, we adopt a wildcard CTC that is both fast and tolerant of ambiguous matches, allowing flexible handling of words that are difficult to match strictly. Since this method does not require retraining of existing models, it can be easily applied to even large-scale models. In experiments on Japanese speech recognition, the proposed method achieved a 29% improvement in the F1 score for unknown words.