logo Idiap Research Institute        
 [BibTeX] [Marc21]
Feature Mapping of Multiple Beamformed Sources for Robust Overlapping Speech Recognition Using a Microphone Array
Type of publication: Idiap-RR
Citation: Li_Idiap-RR-17-2014
Number: Idiap-RR-17-2014
Year: 2014
Month: 10
Institution: Idiap
Note: IEEE/ACM Trans. on Audio, Speech and Language Processing
Abstract: This paper introduces a non-linear vector-based feature mapping approach to extract robust features for au- tomatic speech recognition (ASR) of overlapping speech using a microphone array. We explore different configurations and additional sources of information to improve the effectiveness of the feature mapping. Firstly, we investigate the full-vector based mapping of different sources in a log mel-filterbank energy (log MFBE) domain, and demonstrate that re-training the acoustic model using the generated training data can help improve the recognition performance. Then we investigate the feature mapping between different domains. Finally in order to improve the qualities of the mapping inputs we propose a non-linear mapping of the features from multiple beamformed sources, which are directed at the target and interfering speakers respectively. We demonstrate the effectiveness of the proposed approach through extensive evaluations on the MONC corpus, which includes non-overlapping single speaker and overlapping multi-speaker conditions.
Keywords:
Projects Idiap
AMIDA
IM2
Authors Li, Weifeng
Wang, Longbiao
Zhou, Yicong
Dines, John
Magimai.-Doss, Mathew
Bourlard, Hervé
Liao, Qingmin
Added by: [ADM]
Total mark: 0
Attachments
  • Li_Idiap-RR-17-2014.pdf (MD5: 1eae444048a8923a07106bd3c8f59478)
Notes