Most conventional features used in speaker authentication are based on estimation of spectral envelopes in one way or another, e.g., Mel-scale Filterbank Cepstrum Coefficients (MFC...
Norman Poh Hoon Thian, Conrad Sanderson, Samy Beng...
This paper presents the design and implementation of an adaptive open-set speaker identification system with genetic learning classifier systems. One of the challenging problems i...
WonKyung Park, Jae C. Oh, Misty K. Blowers, Matt B...
—With the increase in cheap commercially available sensors, recording meetings is becoming an increasingly practical option. With this trend comes the need to summarize the recor...
Hayley Hung, Yan Huang, Gerald Friedland, Daniel G...
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...
We propose a method that uses the participants’ head orientation and utterances for automatically identifying the addressee of each utterance in face-to-face multiparty conversa...