Improved training of excitation for HMM-based parametric speech synthesis

INTERSPEECH2010: 11th Annual Conference of the International Speech Communication Association, September 26-30, 2010, Chiba, Japan.

Computer Science

View graph Source

Paper

Full text

Improved training of excitation for HMM-based parametric speech synthesis

Semantic Scholar · Computer Science · 2010

Abstract

INTERSPEECH2010: 11th Annual Conference of the International Speech Communication Association, September 26-30, 2010, Chiba, Japan.

Source of record · Semantic Scholar

References (15)

01A decision tree-based clustering approach to state definition in an excitation modeling framework for HMM-based speech synthesisR. Maia, Tomoki Toda, K. Tokuda et al.2009 · Interspeech · 4 citations

02Trajectory training considering global variance for HMM-based speech synthesisTomoki Toda, S. Young2009 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 30 citations

03A trainable excitation model for HMM-based speech synthesisR. Maia, Tomoki Toda, H. Zen et al.2007 · Interspeech · 18 citations

04An excitation model for HMM-based speech synthesis based on residual modelingR. Maia, Tomoki Toda, H. Zen et al.2007 · Speech Synthesis Workshop · 92 citations

05Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in soundsHideki Kawahara, Ikuyo Masuda-Katsuse, A. Cheveigné1999 · Speech Communication · 2.1k citations

06An adaptive algorithm for mel-cepstral analysis of speechToshiaki Fukada, K. Tokuda, Takao Kobayashi et al.1992 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 410 citations

07Universal coding, information, prediction, and estimationJ. Rissanen1984 · IEEE Transactions on Information Theory · 1.0k citations

08HMM-based Finnish text-to-speech system utilizing glottal inverse filteringT. Raitio, Antti Suni, Hannu Pulakka et al.2008 · Interspeech · 58 citations

09Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005H. Zen, Tomoki Toda, Masaru Nakamura et al.2007 · IEICE Trans. Inf. Syst. · 257 citations

10Towards an improved modeling of the glottal source in statistical parametric speech synthesisJoão P. Cabral, S. Renals, Korin Richmond et al.2007 · Speech Synthesis Workshop · 76 citations

11Improving Arabic HMM based speech synthesis qualityOssama Abdel-Hamid, Sherif M. Abdou, M. Rashwan2006 · Interspeech · 41 citations

12Speech Coding Algorithms2003

Scroll for more · 3 remaining

Similar papers

Modeling of Speech Parameter Sequence Considering Global Variance for HMM-Based Speech SynthesisTomoki Toda2011 · 12 citations In Library

Statistical Approaches to Excitation Modeling in HMM-Based Speech SynthesisJune Sig Sung, Doo Hwa Hong, Hyun Woo Koo et al.2013 · IEICE Trans. Inf. Syst. · 6 citations In Library

Excitation modelling using epoch features for statistical parametric speech synthesisM. K. Reddy, K. Rao2020 · Computer Speech and Language · 14 citations In Library

A Deterministic plus Stochastic Model of the Residual Signal for Improved Parametric Speech SynthesisThomas Drugman, G. Wilfart, T. Dutoit2019 · Interspeech · 101 citations In Library

Hidden-Markov-Model Based Speech EnhancementDaniel Dzibela, A. Sehr2017 · arXiv.org · 2 citations In Library

Modeling and interpolation of Austrian German and Viennese dialect in HMM-based speech synthesisMichael Andreas Pucher, Dietmar Schabus, J. Yamagishi et al.2010 · Speech Communication · 49 citations In Library

Modeling unvoiced sounds in statistical parametric speech synthesis with a continuous vocoderT. Csapó, G. Németh, M. Cernak et al.2016 · European Signal Processing Conference · 19 citations In Library

Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2011Kei Hashimoto, Shinji Takaki, Keiichiro Oura et al.2011 · Blizzard Challenge · 1 citation In Library

Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2010Keiichiro Oura, Kei Hashimoto, Sayaka Shiota et al.2010 · Blizzard Challenge · 0 citations In Library

Reducing over-smoothness in HMM-based speech synthesis using exemplar-based voice conversionG. Nguyen, Trung-Nghia Phung2017 · EURASIP Journal on Audio, Speech, and Music Processing · 8 citations In Library

Source of record

Semantic Scholar

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal