In the framework of Hidden Markov Models (HMM) or hybrid HMM/Artiicial Neural Network (ANN) systems, we present a new approach t o wards automatic speech recognition (ASR). The general idea is to divide up the full frequency band (represent e d i n t e r m s o f critical bands) into several subbands, compute phone probabilities for each sub-band on the basis of subband acoustic features, perfor...

We present the concept of a "Segmental Neural Net" (SNN) for phonetic modeling in continuous speech recognition. The SNN takes as input all the frames of a phonetic segment and gives as output an estimate of the probability of each of the phonemes, given the input segment. By taking into account all the frames of a phonetic segment simultaneously, the SNN overcomes the wellknown conditional-ind...

It is well known that HMM is ineffective in modeling the dynamics of speech due to the piecewise stationary and the independent observation assumptions. In this paper, we propose an analytically tractable framework in which the two modeling techniques are combined to reach a jointly optimal decision in both training and recognition. The combination is achieved by coupling the hidden processes f...

In this paper a framework for maximum a posteriori (MAP) estimation of hidden Markov models (HMM) is presented. Three key issues of MAP estimation, namely the choice of prior distribution family, the specification of the parameters of prior densities and the evaluation of the MAP estimates, are addressed. Using HMMs with Gaussian mixture state observation densities as an example, it is assumed ...

Recognizing human emotions/attitudes from speech cues has gained increased attention recently. Most previous work has focused primarily on suprasegmental prosodic features calculated at the utterance level for modeling against details at the segmental phoneme level. Based on the hypothesis that different emotions have varying effects on the properties of the different speech sounds, this paper ...

Here we seek to understand the similarities and differences between two speech recognition approaches, namely the HMM/ANN hybrid and the posterior-based segmental model. Both these techniques create local posterior probability estimates and combine these estimates into global posteriors – but they are built on somewhat different concepts and mathematical derivations. The HMM/ANN hybrid combines...

In the framework of Hidden Markov Models (HMM) or hybrid HMM/Articial Neural Network (ANN) systems, we present a new approach t o w ards automatic speech recognition (ASR). The general idea is to divide up the full frequency band (represented in terms of critical bands) into several subbands, compute phone probabilities for each sub-band on the basis of subband acoustic features, perform dynami...

Previously, we had developed the concept of a Segmental Neural Net (SNN) for phonetic modeling in continuous speech recognition (CSR). This kind of neural network technology advanced the state-of-the-art of large-vocabulary CSR, which employs Hidden Marlcov Models (HMM), for the ARPA 1oo0-word Resource Management corpus. More Recently, we started porting the neural net system to a larger, more ...

It is well-known that HMMs only of the basic structure cannot capture the correlations among successive frames adequately. In our previous work, to solve this problem, segmental unit HMMs were introduced and their e ectiveness was shown. And the integration of cepstrum and cepstrum into the segmental unit HMMs was also found to improve the recognition performance in the work. In this paper, we ...

We investigate two statistical-detection problems, change-point detection and pattern matching in plasma etch endpoint detection. Our approach is based on a segmental semi-Markov model framework. In the change-point detection problem, the changepoint corresponds to state switching in the model. For pattern matching, the pattern is approximated as a sequence of linear segments which are then mod...