Loading...
Please wait, while we are loading the content...
Similar Documents
A simplified decoding method for a robust distant-talking ASR concept based on feature-domain dereverberation (2008)
| Content Provider | CiteSeerX |
|---|---|
| Author | Sehr, Armin Kellermann, Walter |
| Description | A simplified decoding method for the concept of REverberation MOdeling for Speech recognition (REMOS) [1] is proposed. In order to achieve robust distant-talking Automatic Speech Recognition (ASR), the REMOS concept uses a combination of clean-speech HMMs and a reverberation model to perform feature-domain dereverberation during decoding. The simplified decoding/dereverberation method proposed in this contribution significantly reduces the computational complexity of the concept without a major performance reduction. Index Terms — Dereverberation, robust ASR, reverberation model, feature-domain processing. |
| File Format | |
| Language | English |
| Publisher Date | 2008-01-01 |
| Publisher Institution | Proc. International Workshop for Acoustic Echo and Noise Control (IWAENC |
| Access Restriction | Open |
| Subject Keyword | Simplified Decoding Method Speech Recognition Robust Distant-talking Automatic Speech Recognition Simplified Decoding Dereverberation Method Major Performance Reduction Index Term Dereverberation Feature-domain Dereverberation Remos Concept Feature-domain Processing Robust Distant-talking Asr Concept Reverberation Modeling Reverberation Model Computational Complexity Robust Asr Clean-speech Hmms |
| Content Type | Text |
| Resource Type | Article |
