MDL-based context-dependent subword modeling for speech recognition.

Sairyo, Koichi; Watanabe, Takao

doi:10.1250/ast.21.79

Cited by 192 publications

(123 citation statements)

References 12 publications

Supporting

Mentioning

121

Contrasting

Unclassified

Order By: Relevance

“…Regarding the method for providing context dependency, it should be noted that HSMM normally offers binary decision trees and acoustic models are established for each leaf of these trees, separately [45,46]. Suppose f and L are contextual functions based on a decision tree Y and are defined as…”

Section: Hsmm Structurementioning

confidence: 99%

“…In this experiment, the number of states was 5, and multi-stream left-to-right with no skip path MSD-HSMM was trained as the traditional HSMM system. Decision trees were built using maximum likelihood criterion, and the size of decision trees was determined by MDL principle [46]. Additionally, global variance (GV)-based parameter generation algorithm [20,26] and STRAIGHT vocoder were applied in the synthesis phase.…”

Section: Experimental Conditionsmentioning

confidence: 99%

See 1 more Smart Citation

Context-dependent acoustic modeling based on hidden maximum entropy model for statistical parametric speech synthesis

Khorram

Sameti

Bahmaninezhad

et al. 2014

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Decision tree-clustered context-dependent hidden semi-Markov models (HSMMs) are typically used in statistical parametric speech synthesis to represent probability densities of acoustic features given contextual factors. This paper addresses three major limitations of this decision tree-based structure: (i) The decision tree structure lacks adequate context generalization. (ii) It is unable to express complex context dependencies. (iii) Parameters generated from this structure represent sudden transitions between adjacent states. In order to alleviate the above limitations, many former papers applied multiple decision trees with an additive assumption over those trees. Similarly, the current study uses multiple decision trees as well, but instead of the additive assumption, it is proposed to train the smoothest distribution by maximizing entropy measure. Obviously, increasing the smoothness of the distribution improves the context generalization. The proposed model, named hidden maximum entropy model (HMEM), estimates a distribution that maximizes entropy subject to multiple moment-based constraints. Due to the simultaneous use of multiple decision trees and maximum entropy measure, the three aforementioned issues are considerably alleviated. Relying on HMEM, a novel speech synthesis system has been developed with maximum likelihood (ML) parameter re-estimation as well as maximum output probability parameter generation. Additionally, an effective and fast algorithm that builds multiple decision trees in parallel is devised. Two sets of experiments have been conducted to evaluate the performance of the proposed system. In the first set of experiments, HMEM with some heuristic context clusters is implemented. This system outperformed the decision tree structure in small training databases (i.e., 50, 100, and 200 sentences). In the second set of experiments, the HMEM performance with four parallel decision trees is investigated using both subjective and objective tests. All evaluation results of the second experiment confirm significant improvement of the proposed system over the conventional HSMM.

show abstract

Section: Hsmm Structurementioning

confidence: 99%

Section: Experimental Conditionsmentioning

confidence: 99%

Context-dependent acoustic modeling based on hidden maximum entropy model for statistical parametric speech synthesis

Khorram

Sameti

Bahmaninezhad

et al. 2014

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

show abstract

“…Clustering is performed by means of binary decision trees. In the training phase, the Minimum Description Length (MDL) criterion is used to construct these decision trees [19]. The size of the trees can be controlled through the penalty term α (where α is typically set to 1).…”

Section: Hmm-basedmentioning

confidence: 99%

Statistical Text-to-Speech Synthesis of Spanish Subtitles

Piqueras

Del-Agua

Giménez

et al. 2014

Advances in Speech and Language Technologies for Iberian Languages

View full text Add to dashboard Cite

Abstract. Online multimedia repositories are growing rapidly. However, language barriers are often difficult to overcome for many of the current and potential users. In this paper we describe a TTS Spanish system and we apply it to the synthesis of transcribed and translated video lectures. A statistical parametric speech synthesis system, in which the acoustic mapping is performed with either HMM-based or DNN-based acoustic models, has been developed. To the best of our knowledge, this is the first time that a DNN-based TTS system has been implemented for the synthesis of Spanish. A comparative objective evaluation between both models has been carried out. Our results show that DNN-based systems can reconstruct speech waveforms more accurately.

show abstract

“…To relieve the problem by merging similar training sets, various types of context clustering techniques have been proposed. [2][3][4][5][6] The Minimum Description Length (MDL)-based context clustering algorithm is the most popular one. [2][3] The HMM parameters, i.e.…”

Section: Introductionmentioning

confidence: 99%

“…[2][3][4][5][6] The Minimum Description Length (MDL)-based context clustering algorithm is the most popular one. [2][3] The HMM parameters, i.e. mean vector and covariance matrix, having the similar statistics are tied to the same contextdependent HMM states by the contextual dependent questions.…”

Section: Introductionmentioning

confidence: 99%

Decision Tree Based Context Clustering with Cross Likelihood Ratio for HMM-based TTS

Jung¹,

Kang²

2013

The Journal of the Acoustical Society of Korea

View full text Add to dashboard Cite

This paper proposes a decision tree based context clustering algorithm for HMM-based speech synthesis systems using the cross likelihood ratio with a hierarchical prior (CLRHP). Conventional algorithms tie the context-dependent HMM states that have similar statistical characteristics, but they do not consider the statistical similarity of split child nodes, which does not guarantee the statistical difference between the final leaf nodes. The proposed CLRHP algorithm improves the reliability of model parameters by taking a criterion of minimizing the statistical similarity of split child nodes. Experimental results verify the superiority of the proposed approach to conventional ones.

show abstract

MDL-based context-dependent subword modeling for speech recognition.

Cited by 192 publications

References 12 publications

Context-dependent acoustic modeling based on hidden maximum entropy model for statistical parametric speech synthesis

Context-dependent acoustic modeling based on hidden maximum entropy model for statistical parametric speech synthesis

Statistical Text-to-Speech Synthesis of Spanish Subtitles

Decision Tree Based Context Clustering with Cross Likelihood Ratio for HMM-based TTS

Contact Info

Product

Resources

About