Explicit modelling of state occupancy in hidden Markov models for automatic speech recognition

Russell, Martin J.; Moore, Roger K.

doi:10.1109/icassp.1985.1168477

Cited by 177 publications

(127 citation statements)

References 11 publications

Supporting

Mentioning

126

Contrasting

Order By: Relevance

“…Using the HSMMs, the explicit state duration probability is incorporated into HMMs and the state duration probability is reestimated by using EM algorithm (Russell and Moore, 1985). Note that each context dependent HSMM corresponds to a phoneme-sized speech unit.…”

Section: Experimental Conditionsmentioning

confidence: 99%

Analysis of Decision Trees in Context Clustering of Hidden Markov Model Based Thai Speech Synthesis

Chomphan¹

2011

Journal of Computer Science

View full text Add to dashboard Cite

Problem statement: In Thai speech synthesis using Hidden Markov model (HMM) based synthesis system, the tonal speech quality is degraded due to tone distortion. This major problem must be treated appropriately to preserve the tone characteristics of each syllable unit. Since tone brings about the intelligibility of the synthesized speech. It is needed to establish the tone questions and other phonetic questions in tree-based context clustering process accordingly. Approach: This study describes the analysis of questions in tree-based context clustering process of an HMM-based speech synthesis system for Thai language. In the system, spectrum, pitch or F0 and state duration are modeled simultaneously in a unified framework of HMM, their parameter distributions are clustered independently by using a decision-tree based context clustering technique. The contextual factors which affect spectrum, pitch and duration, i.e., part of speech, position and number of phones in a syllable, position and number of syllables in a word, position and number of words in a sentence, phone type and tone type, are taken into account for constructing the questions of the decision tree. All in all, thirteen sets of questions are analyzed in comparison. Results: In the experiment, we analyzed the decision trees by counting the number of questions in each node coming from those thirteen sets and by calculating the dominance score given to each question as the reciprocal of the distance from the root node to the question node. The highest number and dominance score are of the set of phonetic type, while the second, third highest ones are of the set of part of speech and tone type. Conclusion: By counting the number of questions in each node and calculating the dominance score, we can set the priority of each question set. All in all, the analysis results bring about further development of Thai speech synthesis with efficient context clustering process in an HMM-based speech synthesis system.

show abstract

Section: Experimental Conditionsmentioning

confidence: 99%

Analysis of Decision Trees in Context Clustering of Hidden Markov Model Based Thai Speech Synthesis

Chomphan¹

2011

Journal of Computer Science

View full text Add to dashboard Cite

show abstract

“…These inconsistencies can degrade the quality of synthesized speech. To resolve this discrepancy, hidden semi-Markov models (Ferguson, 1980;Russell and Moore, 1985;Levinson, 1986), which can be viewed as HMMs with explicit state-duration distributions, were introduced (Zen et al, 2007d). The use of HSMMs makes it possible to simultaneously re-estimate state-output and state-duration distributions.…”

Section: Better Duration Modelmentioning

confidence: 99%

Statistical Parametric Speech Synthesis

Black

Zen

Tokuda

2007

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07

211

View full text Add to dashboard Cite

This review gives a general overview of techniques used in statistical parametric speech synthesis. One instance of these techniques, called hidden Markov model (HMM)-based speech synthesis, has recently been demonstrated to be very effective in synthesizing acceptable speech. This review also contrasts these techniques with the more conventional technique of unit-selection synthesis that has dominated speech synthesis over the last decade. The advantages and drawbacks of statistical parametric synthesis are highlighted and we identify where we expect key developments to appear in the immediate future.

show abstract

“…Some approaches started by directly introducing continuously variable duration into the HMM. In (Russell & Cook, 1987) and (Bonafonte et al, 1996), each HMM state is expanded to a sub-HMM (ESHMM) that shares the same emission probability density and performs the correct state duration distribution using its own topology and transition probability. To reduce the loss of efficiency introduced by the ESHMM, a post-processor duration model can be implemented (Wu et al, 2005) using the output of a Viterbi algorithm and ranking the proposed paths through the use of better models for state duration.…”

Section: Modelling Temporal Evolution Using Temporal and Trajectory Mmentioning

confidence: 99%

Double Layer Architectures for Automatic Speech Recognition Using HMM

Casar¹,

Fonollosa²

2007

Robust Speech Recognition and Understanding

View full text Add to dashboard Cite

Explicit modelling of state occupancy in hidden Markov models for automatic speech recognition

Cited by 177 publications

References 11 publications

Analysis of Decision Trees in Context Clustering of Hidden Markov Model Based Thai Speech Synthesis

Analysis of Decision Trees in Context Clustering of Hidden Markov Model Based Thai Speech Synthesis

Statistical Parametric Speech Synthesis

Double Layer Architectures for Automatic Speech Recognition Using HMM

Contact Info

Product

Resources

About