We describe a new GMM-UBM speaker recognition system that uses standard cepstral features, but selects different frames of speech for different subsystems. Subsystems, or “const...
Detection of filled pauses is a challenging research problem which has several practical applications. It can be used to evaluate the spoken fluency skills of the speaker, to im...
Kartik Audhkhasi, Kundan Kandhway, Om Deshmukh, As...
Information distillation techniques are used to analyze and interpret large volumes of speech and text archives in multiple languages and produce structured information of interes...
This paper compares the identification rates of a speaker recognition system using several parameterizations, with special emphasis on the residual signal obtained from linear and...
In this paper we propose a computational model for human-agent and agent-agent conversation. This model has two fundamental characteristics: (1) it takes into account the implicit ...