Sasindran, Z and Tamma, PV (2021) Word-level beam search decoding and correction algorithm (WLBS) for end-to-end ASR. In: 1st International Conference on AI-ML-Systems, AIMLSystems 2021, 21-23 Oct 2021.
PDF
AIMLS_2021.pdf - Published Version Restricted to Registered users only Download (679kB) | Request a copy |
Abstract
A key challenge in resource-constrained speech recognition applications is the unavailability of a large, domain-specific audio corpus to train the models. In such scenarios, models may not be exposed to a wide range of domain-specific words and phrases. In this work, we propose an approach to improve the in-domain automatic speech recognition results using our word-level beam search decoding and correction algorithm (WLBS). We use a token-based language model to mitigate the data sparsity and the out of vocabulary issues in the corpus. We evaluate the proposed approach for airplane-cabin specific announcements use case. The experimental results show that the WLBS algorithm with its handling of misspellings and missing words achieves better performance than state-of-the-art beam search decoding and n-gram LMs. We report a WER of 11.48 on our airplane-cabin announcement test corpus. © 2021 ACM.
Item Type: | Conference Paper |
---|---|
Publication: | ACM International Conference Proceeding Series |
Publisher: | Association for Computing Machinery |
Additional Information: | The copyright for this article belongs to Association for Computing Machinery |
Keywords: | Aircraft; Computational linguistics; Speech recognition, Automatic speech recognition; Beam search; Beam search decoding; Correction algorithms; Decoding algorithm; Language model; Sequence models; Sequence-to-sequence model; Token-based language model; Word level, Decoding |
Department/Centre: | Division of Electrical Sciences > Electronic Systems Engineering (Formerly Centre for Electronic Design & Technology) |
Date Deposited: | 25 Nov 2021 10:32 |
Last Modified: | 25 Nov 2021 10:32 |
URI: | http://eprints.iisc.ac.in/id/eprint/70493 |
Actions (login required)
View Item |