SEARCH CLSP

Workshops

Robust Speaker Recognition Over Varying Channels

Nowadays, speaker recognition is relatively mature with the basic scheme, where speaker model is trained using target speaker speech and speech from large number of non-target speakers. However, the speech from non-target speakers is typically used only for finding general speech distribution (e.g. UBM). It is not used to find the "directions" important for discriminating between speakers. This scheme is reliable when the training and test data come from the same channel. All current speaker recognition systems are however prone to errors when the channel changes (for example from IP telephone to mobile). In speaker recognition, the "channel" variability can include also to linguistic content of the message, emotions, etc. - all these factors should not be considered by a speaker recognition system. Several techniques, such as feature mapping, eigen-channel adaptation and NAP (nuisance attribute projection) have been devised in the past years to overcome the channel variability. These techniques make use of the large amount of data from many speakers to find and ignore directions with high with-in speaker variability. However, these techniques still do not utilize the data to directly search for directions important for discriminating between speakers.

In an attempt to overcome the above mentioned problem, the research will be concentrate on utilizing the large amount of training data currently available to research community to derive the information, that can help discriminate among speakers and discard the information that can not. We propose direct identification of directions in model parameter space that are the most important for discrimination between speakers. According to our experience from speech and language recognition, the use of discriminative training should significantly improve the performance of acoustic SID system. We also expect that discriminative training will make the explicit modeling of channel variability needless.

The research will be based on an excellent baseline - the STBU system for NIST 2006 SRE evaluations (NIST rules prohibit us to disclose the exact position of the system in the evaluations).

The data to be used during the workshop will include NIST SRE data (telephone) but we will not overhear the requests from the security/defense community and evaluate the investigated techniques also on other data sources (meetings, web-radio, etc) as well as on cross-channel conditions.

The expected outcomes of the proposed research are:

1. significant increasing of the accuracy of current SID systems
2. decreasing the dependency on communication channel, content of the message and other factors negatively affecting SID performance.
3. speaker identification and verification from very short speech segments.

Team Members

Team Leader
	Lukas Burget	burget at fit dot vutbr dot cz	Brno University of Technology
Senior Personnel
	Niko Brummer	niko dot brummer at gmail dot com	Spescom DataVoice
	Patrick Kenny	pkenny at crim dot ca	Centre de Recherche en Informatique de Montreal
	Jason Pelecanos	jwpeleca at us dot ibm dot com	IBM
	Douglas Reynolds	dar at sst dot ll dot mit dot edu	MIT Lincoln Labs
	Robbie Vogt	r dot vogt at qut dot edu dot au	Queensland University of Technology
Graduate Students
	Fabio Castaldo	fabio dot castaldo at polito dot it	Polytechnic University of Turin
	Najim Dehak	Najim dot Dehak at crim dot ca	Ecole de Technologie Superieure
	Reda Dehak	reda at dehak dot org	EPITA
	Ondrej Glembek	glembek at fit dot vutbr dot cz	Brno University of Technology
	Zahi Karam	zahi at mit dot edu	Massachusettes Institute of Technology
Undergraduate Students
	John Noecker Jr.	jnoecker at gmail dot com	Duquesne University
	Elly (Hye Young) Na	hna at gmu dot edu	George Mason University
	Ciprian Constantin Costin	cip123a at gmail dot com	The Alexandru Ioan Cuza University
	Valiantsina Hubeika	xhubei00 at stud dot fit dot vutbr dot cz	Brno University of Technology
Affiliates
	Sachin Kajarekar	sachin at speech dot sri dot com	SRI International
	Nicolas Scheffer	scheffer dot nicolas at gmail dot com	SRI International