We introduce the Line Search A-Function (LSAF) technique that generalizes the Extended-Baum Welch technique in order to provide an effective optimization technique for a broader s...
Dimitri Kanevsky, David Nahamoo, Tara N. Sainath, ...
In this paper, we extend our previous study on discriminative training using non-uniform criteria for speech recognition. The work will put emphasis on how the acoustic modeling i...
This paper presents our work on rapid language adaptation of acoustic models based on multilingual cross-language bootstrapping and unsupervised training. We used Automatic Speech...
Exemplar-based techniques, such as k-nearest neighbors (kNNs) and Sparse Representations (SRs), can be used to model a test sample from a few training points in a dictionary set. ...
Tara N. Sainath, David Nahamoo, Bhuvana Ramabhadra...
Abstract: Designing and implementing multimodal applications that take advantage of several recognitionbased interaction techniques (e.g. speech and gesture recognition) is a diffi...