There are two major approaches to speech recognition: frame-based and segment-based approach. Frame-based approach, e.g. HMM, assumes statistical independence and identical distribution of observation in each state. In addition it incorporates weak duration constrains. Segmentbased approach is computational expensive and rough modelling easilly occurs if not much 'templates' are stored. This pa...

Abstract. This paper presents a stochastic segmental speech recognizer that models the a posteriori probabilities directly. The main issues concerning the system are segmental phoneme classification, utterance-level aggregation and the pruning of the search space. For phoneme classification artificial neural networks and support vector machines are applied. Phonemic segmentation and utterance-l...

In this paper, a theoretical framework for Bayesian adaptive training of the parameters of discrete hidden Markov model (DHMM) and of semi-continuous HMM (SCHMM) with Gaussian mixture state observation densities is presented. In addition to formulating the forward-backward MAP (maximum a posterion’) and the segmental MAP algorithms for estimating the above HMM parameters, a computationally effi...

This paper describes a new scheme for robust speech recognition systems where visual information and acoustic features are merged. Using as robust unit the « pseudo-diphone », we compare a global Hidden Markov Model (HMM) and a Master/Slave HMM through a centisecond preprocessing and through a segmental one. We confirm by experimentation the importance of articulatory features in clean and nois...

Untill recently, state-of-the-art, large-vocabulary, continuous speech recognition (CSR) has employed Hidden Markov Modeling (HMM) to model speech sounds. In an attempt to improve over HMM we developed a hybrid system that integrates HMM technology with neural networks. We present the concept of a "Segmental Neural Net" (SNN) for phonetic modeling in CSR. By taking into account all the frames o...

We present a purely time domain approach to speech processing which identifies waveform samples at the boundaries between glottal pulse periods (in voiced speech) or at the boundaries between unvoiced segments. An efficient algorithm for inferring these boundaries is derived from a simple probabilistic generative model of speech and state of the art results are presented on pitch tracking, voic...

An efficient decoding algorithm for segmental HMMs (SHMMs) is proposed with multi-stage pruning. The generation by SHMMs of a feature trajectory for each state expands the search space and the computational cost of decoding. It is reduced in three ways: pre-cost partitioning, start-node (SN) beam pruning, and conventional endnode (EN) beam pruning. Experiments show that partitioning cuts comput...

The use of Deep Belief Networks (DBN) to pretrain Neural Networks has recently led to a resurgence in the use of Artificial Neural Network Hidden Markov Model (ANN/HMM) hybrid systems for Automatic Speech Recognition (ASR). In this paper we report results of a DBN-pretrained context-dependent ANN/HMM system trained on two datasets that are much larger than any reported previously with DBN-pretr...

“Segmental hidden Markov models” (SHMMs) are intended to overcome important speech-modelling limitations of the conventional-HMM approach by representing sequences (or segments) of features and incorporating the concept of trajectories to describe how features change over time. A novel feature of the approach presented in this paper is that extra-segmental variability between different examples...