[2506.18703] Context Biasing for Pronunciation-Orthography Mismatch in Automatic Speech Recognition

Computer Science > Computation and Language arXiv:2506.18703 (cs) [Submitted on 23 Jun 2025 (v1), last revised 4 Mar 2026 (this version, v3)] Title:Context Biasing for Pronunciation-Orthography Mismatch in Automatic Speech Recognition Authors:Christian Huber, Alexander Waibel View a PDF of the paper titled Context Biasing for Pronunciation-Orthography Mismatch in Automatic Speech Recognition, by Christian Huber and Alexander Waibel View PDF HTML (experimental) Abstract:Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice, however, they often fail to recognize words not seen during training, e.g., named entities, acronyms, or domain-specific special words. To address this problem, many context biasing methods have been proposed; however, these methods may still struggle when they are unable to relate audio and corresponding text, e.g., in case of a pronunciation-orthography mismatch. We propose a method where corrections of substitution errors can be used to improve the recognition accuracy of such challenging words. Users can add corrections on the fly during inference. We show that with this method we get a relative improvement in biased word error rate between 22% and 34% compared to a text-based replacement method, while maintaining the overall performance. Subjects: Computation and Lan...