This paper proposes a way of preparing and recording a speech corpus for unit selection text-to-speech speech synthesis driven by symbolic prosody. The research is focused on a phonetically and prosodically rich sentence selection algorithm. Symbolic description on a deep prosody level is used to enrich the phonetic representation of sentences (by respecting the prosodeme types phones appear in...

A significant source of variation in spontaneous speech is due to intra-speaker pronunciation changes. Previous work in automatic speech recognition has identified several factors that affect pronunciation variability such as phonetic context and speaking rate. This work examines new higher level information sources: syntax and discourse structure, specifically the relationship between these fa...

This paper examines some methodological and empirical issues concerning phonetic detail and phonetic variability and the work they accomplish in everyday talk-in-interaction. By considering the phonetic and sequential design of a variety of conversational practices I show that phonetic aspects of language should in the first instance be understood as shaped by interactional considerations. I ar...

We propose a user-friendly automatic phonetic alignment tool for continuous speech: EasyAlign. It is developed and freely distributed as a plug-in of Praat, the popular speech analysis software. Its main advantage is that one can easily align speech from an orthographic transcription. It requires a few minor manual steps and the result is a multi-level annotation within a TextGrid composed of p...

This experiment tested the advantage of binaural presentation of an interfering noise in a task involving identification of monaurally-presented words. These words were embedded in three types of noise: a stationary noise, a speech-modulated noise and a speech-babble noise, in order to assess energetic and informational masking contributions to binaural unmasking. Our results showed important i...

This paper investigates audio-visual unit selection for the synthesis of photo-realistic, speech-synchronized talking-head animations. These animations are synthesized from recorded video samples of a subject speaking in front of a camera, resulting in a photo-realistic appearance. The lip-synchronization is obtained by optimally selecting and concatenating variable-length video units of the mo...

This thesis proposes a phonetic model of English intonation which is a system for linking the phonological and F0 descriptions of an utterance. It is argued that such a model should take the form of a rigorously defined formal system which does not require any human intuition or expertise to operate. It is also argued that this model should be capable of both analysis (F0 to phonology) and synt...

It has often been claimed that vowel duration tends to be inversely related to approximate average f0 crosslinguistically. In this study, we test the empirical adequacy of this observation by conducting a rigorous typological survey of sound patterns involving level tones and duration. Our data reveals a robust negative correlation between tone height and duration (i.e. the lower the tone, the ...

In this paper a novel approach of English Phonetic Alphabet applicable to Chinese people was introduced. This novel English Phonetic Alphabet was specially designed in line with the characteristics of radio telephone frequency communication in China and pronunciation habit and English level of most of Chinese people; which not only can improve the voice quality and guarantee accurate transfer o...

This paper introduces a model for segment-level phonetic responsiveness. It is based on behavior observed in human-human interaction, and is designed to be integrated into spoken dialogue systems to capture potential phonetic variation and simulate convergence capabilities. Each step in the process is responsible for an aspect of the interaction, including monitoring the input speech and approp...