Optimization and Evaluation of a Coarticulation Model based on Observation and Simulation
スポンサーリンク
概要
- 論文の詳細を見る
A coarticulation model, namely 'carrier model', has been proposed previously by Dang et al. to improve the performance of a physiological articulatory model based speech synthesizer. The carrier model offers a good framework to account for coarticulation in the planning stage, while its parameters need to be refined for improving the performance of the model. This study is to refine the parameters of the carrier model and estimate typical phonetic targets by minimizing the differences between model simulations and observations. A simulation based optimization framework is proposed for this purpose. The framework consists of two layers: obtaining planned targets in a low layer; estimating phonetic targets and optimizing the parameters in a high layer. A direct search method was applied to the low layer due to the non-analytic nature of the articulation model, while the high layer adopts bilevel optimization strategy to decompose the complicated problem into a set of subproblems. Objective and subjective evaluation were conducted by combining the refined carrier model and the learned phonetic targets together using the physiological articulatory model and the average error between observations and simulations was 0.15cm over 153 VCV combinations on the jaw, tongue tip and tongue dorsum, meanwhile mean opinion score(MOS) were improved about 0.28 compared with the sound synthesized by averaged target obtained from electromagnetic midsagittal articulographic (EMMA) data through the physiological articulatory model.
- 社団法人電子情報通信学会の論文
- 2006-07-13
著者
-
Lu Xugang
Atr Spoken Language Communication Research Laboratories
-
Lu Xugang
School Of Information Science Japan Advanced Institute Of Science And Technology
-
Lu Xugang
Japan Advanced Institute Of Science And Technology
-
Dang Jianwu
Japan Advanced Inst. Of Sci. And Technol. Ishikawa Jpn
-
Lu Xugang
Information School Japan Advanced Institute Of Science And Technology
-
Dang Jianwu
Information School Japan Advanced Institute Of Science And Technology
-
WEI Jianguo
Japan Advanced Institute of Science and Technology
関連論文
- Robust voice activity detection based on noise eigenspace
- A model-based investigation of activations of the tongue muscles in vowel production
- Speech Enhancement based on Noise Eigenspace Projection
- A speech enhancement framework based on noise eigenspace projection (音声)
- Comparative evaluation of modulation-transfer-function-based blind restoration of sub-band power envelopes of speech as a front-end processor for automatic speech recognition systems
- Sub-Band Temporal Envelope Restoration for ASR in Reverberation Environment (国際ワークショップ Frontiers in Speech and Hearing Research)
- Robust speech feature extraction based on auditory neuronal adaptation mechanism
- A Model-Based Learning Process for Modeling Coarticulation of Human Speech(Knowledge, Information and Creativity Support System)
- Normalization of vocal tract shape using radial basis function (音声)
- Normalization of vocal tract shape using radial basis function
- Optimization and Evaluation of a Coarticulation Model based on Observation and Simulation
- Parameter Optimization for a Coarticulation Model Based on Observation and Simulation (国際ワークショップ Frontiers in Speech and Hearing Research)
- Extraction of Low Dimensional Representation of Vowels in Articulatory Space (国際ワークショップ Frontiers in Speech and Hearing Research)
- Comparison of Emotion Perception among Different Cultures
- Investigation of coarticulation in continuous speech of Japanese
- Investigation of coarticulation effects on vocal tract shapes of vowels based on similarity