A tone-modeling technique using a quantized F0 context to improve tone correctness in average-voice-based speech synthesis
Authors:
- Vataya ChunwijitraVCVataya Chunwijitra
- Takashi NoseTNTakashi Nose
- Takao KobayashiTKTakao Kobayashi
- 1 February 2012
- journal article
- research article
- Published by Elsevier in Speech Communication
- Vol. 54 (2) , 245-255
Abstract
No abstract availableKeywords
This publication has 21 references indexed in Scilit:
- HMM-based speech synthesis with unsupervised labeling of accentual context based on F0 quantization and average voice model2010
- Tone correctness improvement in speaker-independent average-voice-based Thai speech synthesisSpeech Communication, 2009
- Tone correctness improvement in speaker dependent HMM-based Thai speech synthesisSpeech Communication, 2008
- A Hidden Semi-Markov Model-Based Speech Synthesis SystemIEICE Transactions on Information and Systems, 2007
- Average-Voice-Based Speech Synthesis Using HSMM-Based Speaker Adaptation and Adaptive TrainingIEICE Transactions on Information and Systems, 2007
- Analysis and modeling of F0 contours for cantonese text-to-speechACM Transactions on Asian Language Information Processing, 2004
- Analysis and synthesis of intonation using the Tilt modelThe Journal of the Acoustical Society of America, 2000
- Restructuring speech representations using a pitch-adaptive time–frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in soundsSpeech Communication, 1999
- The SUS test: A method for the assessment of text-to-speech synthesis intelligibility using Semantically Unpredictable SentencesSpeech Communication, 1996
- Optimal partitioning for classification and regression treesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991