We report results on speaker diarization of French broadcast news and talk shows on current affairs. This speaker diarization process is a multistage segmentation and clustering s...
Vishwa Gupta, Gilles Boulianne, Patrick Kenny, Pie...
We address the problem of minimum mean-squared error (MMSE) estimation where the estimator is constrained to belong to a prede ned set of functions. We derive a simple closed form...
In this paper we present an approach for speech recognition of multiple languages with constrained resources on embedded devices. Examples of such systems are navigation systems, ...
Resource allocation is considered for cooperative transmissions in multiple-relay wireless networks. Two auction mechanisms, SNR auctions and power auctions, are proposed to distr...
Jianwei Huang, Zhu Han, Mung Chiang, H. Vincent Po...
In this paper, we investigate acoustic features which differentiate the two speech registers neutral and intimate within different constellations of speakers and addressees. Three...
Harmonic + Noise model (HNM) is a hybrid model of speech with a harmonic component and a noise component. While harmonic part describes efficiently the periodicities in speech si...
This paper describes a referential semantic language model that achieves accurate recognition in user-defined domains with no available domain-specific training corpora. This mo...
We present a novel classification model that is formulated as a ratio of semi-definite polynomials. We derive an efficient learning algorithm for this classifier, and apply it...
Conditional Random Fields (CRFs) are often estimated using an entropy based criterion in combination with Generalized Iterative Scaling (GIS). GIS offers, upon others, the immedi...