The HMM-based speech synthesis system (HTS) version 2.0
نویسندگان
چکیده
A statistical parametric speech synthesis system based on hidden Markov models (HMMs) has grown in popularity over the last few years. This system simultaneouslymodels spectrum, excitation, and duration of speech using context-dependent HMMs and generatesspeechwaveforms from the HMMs themselves. Since December 2002, we have publicly released an open-source software toolkit named HMM-based speech synthesis system (HTS) to provide a research and development platform for the speech synthesis community. In December 2006, HTS version 2.0 was released. This version includes a number of new features which are useful for both speech synthesis researchers and developers. This paper describes HTS version 2.0 in detail, as well as future release plans.
منابع مشابه
An Hmm-based Speech Synthesis System Applied to English
This paper describes an HMM-based speech synthesis system (HTS), in which speech waveform is generated from HMMs themselves, and applies it to English speech synthesis using the general speech synthesis architecture of Festival. Similarly to other datadriven speech synthesis approaches, HTS has a compact language dependent module: a list of contextual factors. Thus, it could easily be extended ...
متن کاملFlexible Harmonic/stochastic Modeling for Hmm-based Speech Synthesis
In this paper the preliminary results, of a new approach on speech modeling for statistical parametric HMM-based speech synthesis are presented. The proposed system is based on a flexible pitch-asynchronous harmonic/stochastic model (HSM) [1]. The speech is modeled as the superposition of two components: a harmonic component and a stochastic or aperiodic component. The fact that the synthesis m...
متن کاملDetails of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005
In January 2005, an open evaluation of corpus-based textto-speech synthesis systems using common speech datasets, named Blizzard Challenge 2005, was conducted. Nitech group participated to this challenge with a newly designed HMM-based speech synthesis system (Nitech-HTS 2005). In the present paper, technical details, building processes, and the performance of the Nitech-HTS 2005 voices are des...
متن کاملelite-HTS: a NLP tool for French HMM-based speech synthesis
This paper presents eLite-HTS, a web service which generates input files for the training and synthesis stages of a French HMM-based synthesizer using the HTS toolkit.
متن کاملSpeaker-Independent HMM-based Speech Synthesis System
This paper describes an HMM-based speech synthesis system developed by the HTS working group for the Blizzard Challenge 2007. To further explore the potential of HMM-based speech synthesis, we incorporate new features in our conventional system which underpin a speaker-independent approach: speaker adaptation techniques; adaptive training for HSMMs; and full covariance modeling using the CSMAPL...
متن کامل