Deep neural network-based statistical parametric speech synthesis system using improved time-frequency trajectory excitation model

Eunwoo Song, Hong Goo Kang

Research output: Contribution to journalConference article

5 Citations (Scopus)

Abstract

This paper proposes a deep neural network (DNN)-based statistical parametric speech synthesis system using an improved time-frequency trajectory excitation (ITFTE) model. The ITFTE model, which efficiently reduces the parametric redundancy of a TFTE model, improved the perceptual quality of the vocoding process and the estimation accuracy of the training process. However, there remain problems related to training ITFTE parameters in a hidden Markov model (HMM) framework, such as inefficiency of representing cross-dimensional correlations between ITFTE parameters, over-smoothed outputs caused by statistical averaging, and an over-fitted model due to a decision tree-based state clustering paradigm. To alleviate these limitations, a centralized DNN replaces the decision trees of the HMM training process. Analysis of trainability confirms that the DNN training process improves the model accuracy, which results in improved perceptual quality of synthesized speech. Objective and subjective test results also verify that the proposed system performs better than the conventional HMM-based system.

Original languageEnglish
Pages (from-to)874-878
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2015-January
Publication statusPublished - 2015 Jan 1

Fingerprint

Speech Synthesis
Speech synthesis
Excitation
Trajectories
Neural Networks
Trajectory
Hidden Markov models
Markov Model
Decision trees
Decision tree
Model
Redundancy
Averaging
Paradigm
Deep neural networks
Clustering
Model-based
Verify
Training
Output

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Cite this

@article{21467d728fcb4c66a61a4e728f5549d0,
title = "Deep neural network-based statistical parametric speech synthesis system using improved time-frequency trajectory excitation model",
abstract = "This paper proposes a deep neural network (DNN)-based statistical parametric speech synthesis system using an improved time-frequency trajectory excitation (ITFTE) model. The ITFTE model, which efficiently reduces the parametric redundancy of a TFTE model, improved the perceptual quality of the vocoding process and the estimation accuracy of the training process. However, there remain problems related to training ITFTE parameters in a hidden Markov model (HMM) framework, such as inefficiency of representing cross-dimensional correlations between ITFTE parameters, over-smoothed outputs caused by statistical averaging, and an over-fitted model due to a decision tree-based state clustering paradigm. To alleviate these limitations, a centralized DNN replaces the decision trees of the HMM training process. Analysis of trainability confirms that the DNN training process improves the model accuracy, which results in improved perceptual quality of synthesized speech. Objective and subjective test results also verify that the proposed system performs better than the conventional HMM-based system.",
author = "Eunwoo Song and Kang, {Hong Goo}",
year = "2015",
month = "1",
day = "1",
language = "English",
volume = "2015-January",
pages = "874--878",
journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
issn = "2308-457X",

}

TY - JOUR

T1 - Deep neural network-based statistical parametric speech synthesis system using improved time-frequency trajectory excitation model

AU - Song, Eunwoo

AU - Kang, Hong Goo

PY - 2015/1/1

Y1 - 2015/1/1

N2 - This paper proposes a deep neural network (DNN)-based statistical parametric speech synthesis system using an improved time-frequency trajectory excitation (ITFTE) model. The ITFTE model, which efficiently reduces the parametric redundancy of a TFTE model, improved the perceptual quality of the vocoding process and the estimation accuracy of the training process. However, there remain problems related to training ITFTE parameters in a hidden Markov model (HMM) framework, such as inefficiency of representing cross-dimensional correlations between ITFTE parameters, over-smoothed outputs caused by statistical averaging, and an over-fitted model due to a decision tree-based state clustering paradigm. To alleviate these limitations, a centralized DNN replaces the decision trees of the HMM training process. Analysis of trainability confirms that the DNN training process improves the model accuracy, which results in improved perceptual quality of synthesized speech. Objective and subjective test results also verify that the proposed system performs better than the conventional HMM-based system.

AB - This paper proposes a deep neural network (DNN)-based statistical parametric speech synthesis system using an improved time-frequency trajectory excitation (ITFTE) model. The ITFTE model, which efficiently reduces the parametric redundancy of a TFTE model, improved the perceptual quality of the vocoding process and the estimation accuracy of the training process. However, there remain problems related to training ITFTE parameters in a hidden Markov model (HMM) framework, such as inefficiency of representing cross-dimensional correlations between ITFTE parameters, over-smoothed outputs caused by statistical averaging, and an over-fitted model due to a decision tree-based state clustering paradigm. To alleviate these limitations, a centralized DNN replaces the decision trees of the HMM training process. Analysis of trainability confirms that the DNN training process improves the model accuracy, which results in improved perceptual quality of synthesized speech. Objective and subjective test results also verify that the proposed system performs better than the conventional HMM-based system.

UR - http://www.scopus.com/inward/record.url?scp=84959125844&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959125844&partnerID=8YFLogxK

M3 - Conference article

VL - 2015-January

SP - 874

EP - 878

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SN - 2308-457X

ER -