Publication | Closed Access
THE SRI NIST 2008 speaker recognition evaluation system
51
Citations
10
References
2009
Year
Unknown Venue
EngineeringMachine LearningPhonologySpeech RecognitionNatural Language ProcessingPattern RecognitionSpeaker IdentificationPhoneticsSpeaker DiarizationRobust Speech RecognitionVoice RecognitionLanguage StudiesSpeech PerceptionNativeness ConditioningSpeech CommunicationSpecific SubsystemsMulti-speaker Speech RecognitionSri Nist 2008Speech ProcessingVarious Subsystem CombinationsLinguisticsSpeaker Recognition
The SRI speaker recognition system for the 2008 NIST speaker recognition evaluation (SRE) incorporates a variety of models and features, both cepstral and stylistic. We highlight the improvements made to specific subsystems and analyze the performance of various subsystem combinations in different data conditions. We show the importance of language and nativeness conditioning, as well as the role of ASR for speaker verification.
| Year | Citations | |
|---|---|---|
Page 1
Page 1