| Paper ID | SPE-43.5 |
| Paper Title |
REPRESENTATION LEARNING FOR SPEECH RECOGNITION USING FEEDBACK BASED RELEVANCE WEIGHTING |
| Authors |
Purvi Agrawal, Sriram Ganapathy, Indian Institute of Science, India |
| Session | SPE-43: Speech Recognition 15: Robust Speech Recognition 1 |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 16:30 - 17:15 |
| Presentation Time: | Thursday, 10 June, 16:30 - 17:15 |
| Presentation |
Poster
|
| Topic |
Speech Processing: [SPE-ROBU] Robust Speech Recognition |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| 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). |
