In many pattern recognition tasks, given some input data and a family of models, the “best” model is defined as the one which maximizes the likelihood of the data given the m...
Tara N. Sainath, Dimitri Kanevsky, Bhuvana Ramabha...
Past research on automatic laughter detection has focused mainly on audio-based detection. Here we present an audiovisual approach to distinguishing laughter from speech and we sh...
—Sensory inputs such as visual images or audio spectrograms can act as symbols in a new cognitive model. The stability of direct image association operators allows the discrete b...
This paper presents a maximum likelihood (ML) framework for multimicrophone sound source localization (SSL). Besides deriving the framework, we focus on making the connection and ...
Abstract. In this paper, we propose a method for blind source separation (BSS) of convolutive audio recordings with short blocks of stationary sources, i.e. dynamically changing so...