Paper Info
Title
Speaker Diarization For Meeting Room Audio
Abstract
This paper describes a speaker diarization system in 2007 NIST Rich Transcription (RT07) Meeting Recognition Evaluation for the task of Multiple Distant Microphone (MDM) in meeting room scenarios. The system includes three major modules: data preparation, initial speaker clustering and cluster purification/merging. The data preparation consists of the raw data Wiener filtering and beamforming, Time Difference of Arrival estimate and speech activity detection. Based on the initial processed data, two-stage histogram quantization has been used to perform the initial speaker clustering. A modified purification strategy via high-order GMM clustering method is proposed. BIC criterion is applied for cluster merging. The system achieves a competitive overall DER of 8.31% for RT07 MDM speaker diarization task.
Year
Venue
Keywords
2009
INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5
Multiple Distant Microphone, speaker diarization, time difference of arrive, speech activity detection, speaker clustering
Field
DocType
Citations 
Wiener filter,Beamforming,Histogram,Pattern recognition,Voice activity detection,Computer science,Speech recognition,NIST,Speaker diarisation,Artificial intelligence,Cluster analysis,Microphone
Conference
11
PageRank 
References 
Authors
0.85
8
4
Name
Order
Citations
PageRank
Hanwu Sun19814.15
Tin Lay Nwe247934.59
Bin Ma360047.26
Haizhou Li43678334.61