LOCALIZATION OF NON-LINGUISTIC EVENTS IN SPONTANEOUS SPEECH BY NON-NEGATIVE MATRIX FACTORIZATION AND LONG SHORT-TERM MEMORY
Audio/Visual Detection of Non-Linguistic Vocal Outbursts
Přednášející: Felix Weninger, Autoři: Felix Weninger, Björn Schuller, Martin Wöllmer, Gerhard Rigoll, Technische Universität München, Germany
Features generated by Non-Negative Matrix Factorization (NMF) have successfully been introduced into robust speech processing, including noise-robust speech recognition and detection of non-linguistic vocalizations. In this study, we introduce a novel tandem approach by integrating likelihood features derived from NMF into Bidirectional Long Short-Term Memory Recurrent Neural Networks (BLSTM-RNNs) in order to dynamically localize non-linguistic events, i.e., laughter, vocal, and non-vocal noise, in highly spontaneous speech. We compare our tandem architecture to a baseline conventional phoneme-HMM-based speech recognizer, and achieve a relative reduction of the frame error rate by 37.5% in the discrimination of speech and different non-speech segments.
Informace o přednášce
| Nahráno: | 2011-05-25 14:45 - 15:05, Club D |
|---|---|
| Přidáno: | 19. 6. 2011 17:19 |
| Počet zhlédnutí: | 24 |
| Rozlišení videa: | 1024x576 px, 512x288 px |
| Délka videa: | 0:19:47 |
| Audio stopa: | MP3 [6.69 MB], 0:19:47 |
Příbuzné přednášky
0:11:42
ONLINE DETECTION OF VOCAL LISTENER RESPONSES WITH MAXIMUM LATENCY CONSTRAINTS
Audio/Visual Detection of Non-Linguistic Vocal Outbursts
Přidáno: 20. 6. 2011 00:17
0:24:42
AUDIOVISUAL CLASSIFICATION OF VOCAL OUTBURSTS IN HUMAN CONVERSATION USING LONG-SHORT-TERM MEMORY NETWORKS
Audio/Visual Detection of Non-Linguistic Vocal Outbursts
Přidáno: 19. 6. 2011 17:31
Komentáře