A phoneme-based Gaussian mixture VQ codebook can improve the conventional DHMM system performance signiicantly. In this paper, an optimization method for the phoneme-based VQ codebook is proposed. The experimental results shown that the optimized phoneme-based VQ codebook leads to both the improvement of system performance and the reduction of system complexity.

This study investigates the usefulness of wavelet transforms in phoneme recognition. Both discrete wavelet transforms (DWT) and sampled continuous wavelet transforms (SCWT) are tested. The wavelet transform is used as a part of the front-end processor which extracts feature vectors for a speakerindependent HMM-based phoneme recognizer. The results are evaluated on a portion of TIMIT corpus cons...

The phoneme classification inaccuracy at the acoustic phonetic level is a major weakness in most speech recognition systems. However, the inaccuracy will violate phonotactic constraints at the acoustic phonetic level. A better performance is expected if a language model is adopted in a recognition system for post-processing phoneme estimates and making corrections with a set of explicit rules o...

In order to apply speech spectrogram reading heuristics to an automatic speech recognition system, a more accurate expression of the heuristics must be developed. In particular, the transformation between acoustic feature measurements and phoneme candidates must be developed in a quantitative manner. In this paper, a visual acoustic-feature labeland a phoneme identification approach using this ...

This paper proposes a method for the unsupervised learning of lexicons from pairs of a spoken utterance and an object as its meaning without any a priori linguistic knowledge other than a phoneme acoustic model. In order to obtain a lexicon, a statistical model of the joint probability of a spoken utterance and an object is learned based on the minimum description length principle. This model c...

The Phoneme Dedicated Artificial Neural Network (PDANN) segmental duration model consists of a set of ANNs trained specifically for each phoneme segment in order to avoid miscellaneous influence of different types of phoneme segments. Therefore, each ANN is dedicated to predict the duration of a specific phoneme segment. Objective and subjective measurements of the performance of the PDANN mode...

We propose a stochastic phoneme space transformation technique that allows the conversion of conditional source phoneme posterior probabilities (conditioned on the acoustics) into target phoneme posterior probabilities. The source and target phonemes can be in any language and phoneme format such as the International Phonetic Alphabet. The novel technique makes use of a Kullback-Leibler diverge...

We investigate techniques for acoustic modeling in automatic recognition of context-independent phoneme strings from the TIMIT database. The baseline phoneme recognizer is based on TempoRAl Patterns (TRAP). This recognizer is simplified to shorten processing times and reduce computational requirements. More states per phoneme and bi-gram language models are incorporated into the system and eval...

How does the perception of a new phoneme contrast develop? Are differences found across age groups? In answering these questions, we use two alternative hypotheses: i) Acquired Distinctiveness: before learning, differences between and within phoneme categories are relatively hard to discriminate. Through training, the phoneme boundary is learned. ii) Acquired Similarity: before learning, differ...

In this paper, we propose a method for generating a pronunciation dictionary—extracting typical pronunciations for each word from speech data uttered by Japanese speakers—as one approach to speech recognition targeting English speech uttered by Japanese speakers whose mother tongue is not English. This method includes three processes: a process in which English phoneme HMMs (Hidden Markov Model...