This paper describes a method of concatenative speech synthesis that makes use of 3-dimensional labelling of speech, and shows how this can be applied to the synthesis of both mono-lingual and foreign-language speech. The dimensions encode phonetic, prosodic, and voicequality information in order to fully describe the acoustic characteristics of each speech segment.

This paper describes an eye tracking experiment to study the processing of diphone synthesis, unit selection synthesis, and human speech taking segmental and suprasegmental speech quality into account. The results showed that both factors influenced the processing of human and synthetic speech, and confirmed that eye tracking is a promising albeit time consuming research method to evaluate synt...

Advances in speech coding technologies have enabled speech coders to achieve bit-rate reductions at a great extent while maintaining roughly the same speech quality. One of the most important driving forces behind this feat is the analysis-by-synthesis paradigm. Code Excited Linear Predictive coder (CELP) is the quite efficient closed loop analysis-by-synthesis method for narrow and medium band...

This paper describes an eye tracking experiment to study the processing of diphone synthesis, unit selection synthesis, and human speech taking segmental and suprasegmental speech quality into account. The results showed that both factors influenced the processing of human and synthetic speech, and confirmed that eye tracking is a promising albeit time consuming research method to evaluate synt...

We have applied two state-of-the-art speech synthesis techniques (unit selection and HMM-based synthesis) to the synthesis of emotional speech. A series of carefully designed perceptual tests to evaluate speech quality, emotion identification rates and emotional strength were used for the six emotions which we recorded – happiness, sadness, anger, surprise, fear, disgust. For the HMM-based meth...

A method was developed for the corpus-based synthesis of emotional speech. Fundamental frequency (F0) contours were synthesized by predicting command values of the generation process model using binary regression trees with the input of linguistic information of the sentence to be synthesized. Because of the model constraint, a certain quality is still kept in synthesized speech even if the pre...

The absence of alternatives/variants is a dramatical limitation of text-tospeech synthesis compared to the variety of human speech. This paper introduces the use of speech alternatives/variants in order to improve text-to-speech synthesis systems. Speech alternatives denote the variety of possibilities that a speaker has to pronounce a sentence depending on linguistic constraints, specific stra...

This project documents some initial results of our investigation of the applicability of adaptation techniques and procedures for use in speech synthesis systems – a process whereby a welltrained synthesizer can be transformed to sound "more like" a small target recording set. If we can ensure that the target data set is representative not of an individual speaker, but of a category of accented...

This study presents a novel technique to enhance telephone speech signals. This technique is based on the Amplitude and Frequency Modulation (AM-FM) model, which represents the speech signal as the sum of N successive AM-FM signals. Based on a leastmean-square error criterion, each AM-FM signal is modified using an iterative algorithm in order to compensate for the deformation of the signal cau...

This paper proposes a new method for automatically generating speech synthesis units. A small set of synthesis units is selected from a large speech database by the proposed Closed-Loop Training method (CLT). Because CLT is based on the evaluation and minimization of the distortion caused by the synthesis process such as prosodic modi cation, the selected synthesis units are most suitable for s...