Agrawal, P and Ganapathy, S (2021) Representation Learning for Speech Recognition Using Feedback Based Relevance Weighting. In: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6 - 11 June 2021, Virtual, Toronto, pp. 6883-6887.
|
PDF
ICASSP_2021.pdf - Published Version Download (2MB) | Preview |
Abstract
In this work, we propose an acoustic embedding based approach for representation learning in speech recognition. The proposed approach involves two stages comprising of acoustic filterbank learning from raw waveform, followed by modulation filterbank learning. In each stage, a relevance weighting operation is employed that acts as a feature selection module. In particular, the relevance weighting network receives embeddings of the model outputs from the previous time instants as feedback. The proposed relevance weighting scheme allows the respective feature representations to be adaptively selected before propagation to the higher layers. The application of the proposed approach for the task of speech recognition on Aurora-4 and CHiME-3 datasets gives significant performance improvements over baseline systems on raw waveform signal as well as those based on mel representations (average relative improvement of 15 over the mel baseline on Aurora-4 dataset and 7 on CHiME-3 dataset).
Item Type: | Conference Proceedings |
---|---|
Publication: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
Publisher: | Institute of Electrical and Electronics Engineers Inc. |
Additional Information: | The copyright for this article belongs to the Authors. |
Keywords: | Embeddings; Filter banks; Modulation, Baseline systems; Feature representation; Feed-back based; Model outputs; Modulation filterbank; Wave forms; Weighting scheme, Speech recognition |
Department/Centre: | Division of Electrical Sciences > Electrical Communication Engineering > Electrical Communication Engineering - Technical Reports Division of Electrical Sciences > Electrical Engineering |
Date Deposited: | 01 Jun 2023 10:05 |
Last Modified: | 01 Jun 2023 10:05 |
URI: | https://eprints.iisc.ac.in/id/eprint/81734 |
Actions (login required)
View Item |