A postfilter to modify the modulation spectrum in HMM-based speech synthesis
Authors:
- 1 May 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 7 (15206149) , 290-294
Abstract
In this paper, we propose a postfilter to compensate modulation spectrum in HMM-based speech synthesis. In order to alleviate over-smoothing effects which is a main cause of quality degradation in HMM-based speech synthesis, it is necessary to consider features that can capture over-smoothing. Global Variance (GV) is one well-known example of such a feature, and the effectiveness of parameter generation algorithm considering GV have been confirmed. However, the quality gap between natural speech and synthetic speech is still large. In this paper, we introduce the Modulation Spectrum (MS) of speech parameter trajectory as a new feature to effectively capture the over-smoothing effect, and we propose a postfilter based on the MS. The MS is represented as a power spectrum of the parameter trajectory. The generated speech parameter sequence is filtered to ensure that its MS has a pattern similar to natural speech. Experimental results show quality improvements when the proposed methods are applied to spectral and F 0 components, compared with conventional methods considering GV.Keywords
This publication has 13 references indexed in Scilit:
- Statistical parametric speech synthesisSpeech Communication, 2009
- A Style Control Technique for HMM-Based Expressive Speech SynthesisIEICE Transactions on Information and Systems, 2007
- A Hidden Semi-Markov Model-Based Speech Synthesis SystemIEICE Transactions on Information and Systems, 2007
- A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech SynthesisIEICE 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
- Joint Acoustic and Modulation FrequencyEURASIP Journal on Advances in Signal Processing, 2003
- Speech parameter generation algorithms for HMM-based speech synthesis2002
- Speaker interpolation for HMM-based speech synthesis system.Acoustical Science and Technology, 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
- Effect of reducing slow temporal modulations on speech receptionThe Journal of the Acoustical Society of America, 1994