Abstract | ||
---|---|---|
In this paper, we describe the IBM system submitted to the NIST Rich Transcription Spring 2006 (RT06s) evaluation campaign for automatic speech activity detection (SAD). This SAD system has been developed and evaluated on CHIL lecture meeting data using far-field microphone sensors, namely a single distant microphone (SDM) configuration and a multiple distant microphone (MDM) condition. The IBM SAD system employs a three-class statistical classifier, trained on features that augment traditional signal energy ones with features that are based on acoustic phonetic likelihoods. The latter are obtained using a large speaker-independent acoustic model trained on meeting data. In the detection stage, after feature extraction and classification, the resulting sequence of classified states is further collapsed into segments belonging to only two classes, speech or silence, following two levels of smoothing. In the MDM condition, the process is repeated for every available microphone channel, and the outputs are combined based on a simple majority voting rule, biased towards speech. The system performed well at the RT06s evaluation campaign, resulting to 8.62% and 5.01% “speaker diarization error” in the SDM and MDM conditions respectively. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11965152_29 | MLMI |
Keywords | Field | DocType |
chil lecture meeting data,ibm rt06s evaluation system,multiple distant microphone,ibm system,chil seminar,mdm condition,available microphone channel,single distant microphone,ibm sad system,automatic speech activity detection,far-field microphone sensor,sad system,speaker diarization,speech activity detection,feature extraction,system performance | Speech processing,Pattern recognition,Computer science,Voice activity detection,Feature extraction,Speech recognition,NIST,Smoothing,Artificial intelligence,Speaker diarisation,Microphone,Acoustic model | Conference |
Volume | ISSN | ISBN |
4299 | 0302-9743 | 3-540-69267-3 |
Citations | PageRank | References |
3 | 0.44 | 12 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Etienne Marcheret | 1 | 100 | 11.15 |
Gerasimos Potamianos | 2 | 1113 | 113.80 |
Karthik Visweswariah | 3 | 400 | 38.22 |
Jing Huang | 4 | 2464 | 186.09 |