The approach outlined in this paper aims to provide better expressivity of unit selection TTS for dialog intended applications while retaining the natural sounding voice quality typical of unit selection synthesis. A small set of speech acts were used to annotate a corpus from one female US English speaker. The corpus was composed of speech read primarily from interactive dialogs of various kin...

This paper describes a technique for controlling voice quality of synthetic speech using multiple regression hidden semi-Markov model (HSMM). In the technique, we assume that the mean vectors of output and state duration distribution of HSMM are modeled by multiple regression with a parameter vector called voice quality control vector. We first choose three features for controlling voice qualit...

OBJECTIVE In response to the rapidly increasing interest in using human voice in cognitive brain research, a new method, semisynthetic speech generation (SSG), is presented for generation of speech stimuli. METHODS The method synthesizes speech stimuli as a combination of purely artificial processes and processes that originate from the natural human speech production mechanism. SSG first est...

Speech synthesis is the artificial production of human speech. Attempts to control the quality of voice of synthesized speech have existed for more than a decade now. Several prototypes and fully operating systems also have been built based on different synthesis technique. This article reviews recent advances in research and development of speech synthesis with focus on one of the key approach...

The term voice quality or phonation types often come from studies of pathological speech. In normal speech speakers use different phonation types in some languages for linguistic distinction, prosodically as a boundary signal and in attitudes and emotions. Our paper aims to describe the different phonation types that occur in Standard Chinese TV newscasts and the relationship between creaky voi...

BACKGROUND Perceptual voice evaluation is a common clinical tool. However, to date, there is no consensus yet as to which common quality should be measured. Some available evidence shows that voice quality is a language-specific property which may be different across different languages. The familiarity of a language may affect the perception and reliability in rating voice quality. AIMS The ...

It is well known, the voice segments and coincident data packets are not equally valued and significant for decoding and comprehension of speech signal. Some lost segments may only slightly worsen audible quality, while others cause strong distortion of the speech signals. Despite this, the feature of different importance of different voice segments in current generation of digital voice transm...

PURPOSE To evaluate the long-term effects of voice therapy on the life quality of teachers who were discharged or abandoned the voice therapy for dysphonia. METHODS This was a longitudinal study based on analysis of assessments with teachers of municipal schools in Belo Horizonte, who were referred to voice therapy and were discharged or abandoned the speech-language therapy for more than six...

The purpose of this paper is to investigate the accuracy of PESQ and 3SQM in predicting voice quality over live 3G networks. We set up an Asterisk-based testbed to measure voice quality over 3G mobile networks. 192 experiments with speech samples from the ITU-T database were recorded via 3G mobile phones and the results of the objective measurements were analyzed. We further selected 30 samples...