Synthesis of child speech with HMM adaptation and voice conversion

Authors:
Oliver Watts;Junichi Yamagishi;Simon King;Kay Berkling
Affiliations:
Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK;Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK;Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK;Inline Internet Online Dienste GmbH, Karlsruhe, Germany
Venue:
IEEE Transactions on Audio, Speech, and Language Processing
Year:
2010

Citing 7
Cited 1

Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: possible role of a repetitive structure in sounds

Speech Communication
Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005

IEICE - Transactions on Information and Systems
Average-Voice-Based Speech Synthesis Using HSMM-Based Speaker Adaptation and Adaptive Training

IEICE - Transactions on Information and Systems
Multisyn: Open-domain unit selection for the Festival speech synthesis system

Speech Communication
Review: Statistical parametric speech synthesis

Speech Communication
Analysis of Speaker Adaptation Algorithms for HMM-Based Speech Synthesis and a Constrained SMAPLR Adaptation Algorithm

IEEE Transactions on Audio, Speech, and Language Processing
Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory

IEEE Transactions on Audio, Speech, and Language Processing

State-of-the-art in TEL to support social communication skill development in children with autism: a multi-disciplinary review

International Journal of Technology Enhanced Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

The synthesis of child speech presents challenges both in the collection of data and in the building of a synthesizer from that data. We chose to build a statistical parametric synthesizer using the hidden Markov model (HMM)-based system HTS, as this technique has previously been shown to perform well for limited amounts of data, and for data collected under imperfect conditions. Six different configurations of the synthesizer were compared, using both speaker-dependent and speaker-adaptive modeling techniques, and using varying amounts of data. For comparison with HMM adaptation, techniques from voice conversion were used to transform existing synthesizers to the characteristics of the target speaker. Speaker-adaptive voices generally outperformed child speaker-dependent voices in the evaluation. HMM adaptation outperformed voice conversion style techniques when using the full target speaker corpus; with fewer adaptation data, however, no significant listener preference for either HMM adaptation or voice conversion methods was found.