Learn More
In this paper, we extend the Maximum Likelihood (ML) training algorithm to the Minimum Classiica-tion Error (MCE) training algorithm for discriminatively estimating the state-dependent polynomial coeecients in the stochastic trajectory model or the trended HMM originally proposed in 2]. The main motivation of this extension is the new model space for(More)
Compared to the landline network environment, the wireless environment presents new factors affecting ASR performance (or accuracy). Our goal here is to determine these factors, and their relative importance, and then to devise methods to mitigate them. We approach this goal, first, by conducting a set of experiments where we use a state of the art ASR(More)
The addition of a word normalized energy contour uniformly improves performance of the HMM recognizer and makes it more robust to diierence in talker populations. This kind of normalization generally requires some information on the statistics of energy features over the whole utterance, which is not a feasible solution in real-time applications due to the(More)
We i n vestigate a class of features related to voicing parameters that indicate whether the vocal chords are vibrating. Features describing voicing characteristics of speech signals are integrated with an existing 38-dimensional feature vector consisting of rst and second order time derivatives of the frame energy and of the cepstral coeecients with their(More)
This paper addresses the problem of speech recognition under accent variations in English language. It has been demonstrated in previous research efforts that the multi-transitional model architecture is one of the solutions for robust speech recognition. In this study, we describe an universal hybrid system that is trained with data from American,(More)
In this letter, we report our recent work on applications of the combined maximum likelihood linear regression (MLLR) and the minimum classification error training (MCE) approach to estimating the time-varying polynomial Gaussian mean functions in the trended hidden Markov model (HMM). We call this integrated approach the minimum classification error linear(More)
cessing techniques, there are no theoretical reasons why the In this paper, we investigate the interactions of front-end feature extraction and back-end classification techniques in HMM based speech recognizer. This work concentrates on finding the optimal linear transformation of Mel-warped short-time DFT information according to the ininiinuni(More)
The study presented in this work is a first effort at real-time speech translation of TED talks, a compendium of public talks with different speakers addressing a variety of topics. We address the goal of achieving a system that balances translation accuracy and la-tency. In order to improve ASR performance for our diverse data set, adaptation techniques(More)
— In this paper, we extend the maximum likelihood (ML) training algorithm to the minimum classification error (MCE) training algorithm for discriminatively estimating the state-dependent polynomial coefficients in the stochastic tra-jectory model or the trended hidden Markov model (HMM) originally proposed in [2]. The main motivation of this extension is(More)