Recently, a trajectory model, derived from the hidden Markov model (HMM) by imposing explicit relationships between static and dynamic features, has been proposed. The derived model, named trajectory HMM, can alleviate two limitations of the HMM: constant statistics within a state and conditional independence assumption of state output probabilities. In the present paper, a speaker adaptation a...

Observation uncertainty techniques offer a way to dynamically compensate automatic speech recognizers to account for the information missing in real world scenarios. These techniques have been demonstrated to effectively be able to compensate multiple environment distortions and improve the integration of ASR systems with speech enhancement pre-processing through uncertainty propagation. Unfort...

In this paper we use kernel-based Fisher Discriminants (KFD) for classification by integrating this method in a HMM-based speech recognition system. We translate the outputs of the KFD-classifier into conditional probabilities and use them as production probabilities of a HMM-based decoder for speech recognition. To obtain a good performance also in terms of computational complexity the Recursi...

Progress on speech recognition of Thai digit strings is presented in this paper. HTK 3.0 was chosen to implement the HMM-based speech recognizer. MFCCs and their delta and delta-delta terms were used as speech features. Several set of HMM parameters were investigated. Two kinds of word searching methods were tried. Recognition accuracy of 98.7% on test data was achieved with a fixed length word...

in order to the enhancement of the quality of speech corrupted by additive noise, a speech enhancement method has been put forward based on the combination of spectral subtraction and binary masking. spectral subtraction is a powerful method for removing noise from speech and binary masking provides essential elements to be used in monaural speech segregation. in the proposed combined method, f...

This paper presents new adaptive filtering techniques used in speech enhancement system. Adaptive filtering schemes are subjected to different trade-offs regarding their steady-state misadjustment, speed of convergence, and tracking performance. Fractional Least-Mean-Square (FLMS) is a new adaptive algorithm which has better performance than the conventional LMS algorithm. Normalization of LMS ...

A new technique is proposed to estimate the robust continuous observation densities of hidden Markov model (HMM) for improving the performance of speaker-independent (SI) automatic speech recognition system. First, a scheme of generalized common vector (GCV), which originated from the common vector approach (CVA), is proposed. The objective of this scheme is to extract a robust speech feature o...

We present our approach to unsupervised training of speech recognizers. Our approach iteratively adjusts sound units that are ptimized for the acoustic domain of interest. We thus enable the use of speech recognizers for applications in speech domains here transcriptions do not exist. The resulting recognizer is a state-of-the-art recognizer on the optimized units. Specifically we ropose buildi...

Models for automatic speech recognition (ASR) hold detailed information about spectral and spectro-temporal characteristics of clean speech signals. Using these models for speech enhancement is desirable and has been the target of past research efforts. In such model-based speech enhancement systems, a powerful ASR is imperative. To increase the recognition rates especially in low-SNR condition...

In this paper we address the problem of enhancing speech which has been degraded by additive noise. As proposed by Ephraim et al., autoregressive hidden Markov models (AR-HMM) for the clean speech and an autoregressive Gaussian for the noise are used. The filter applied to a given frame of noisy speech is estimated using the noise model and the autoregressive Gaussian having the highest a poste...