An extension of HMM-based speech synthesis is proposed to reproduce natural speech sounds. For compression of large amounts of speech, the use of speech synthesizers has an advantage in terms of the size of compressed data. However, the quality of synthetic speech is often inferior to that of speech compressed by general-purpose speech codecs such as CELP, where prosodic features are reproduced...

The Weather Report Synthesizer is a speech synthesis system for weather forecasts in Greek. Instead of trying to improve the synthesis quality of PSOLA based diphone concatenation speech synthesizers, we have chosen to use words as the synthesis units. This approach has the advantage of low complexity and quick implementation, while at the same time it achieves better speech quality due to the ...

This paper describes CU VOCAL, a Chinese text-to-speech synthesis system that adopts the approach of corpus-based syllable concatenation. We have demonstrated the applicability of the approach primarily for Cantonese, a major dialect of Chinese predominant in Hong Kong, South China and many overseas Chinese communities. This work extends our previous work as described in [1]. Our approach is ab...

The paper presents the capability of an HMM-based TTS system to produce Bengali speech. In this synthesis method, trajectories of speech parameters are generated from the trained Hidden Markov Models. A final speech waveform is synthesized from those speech parameters. In our experiments, spectral properties were represented by Mel Cepstrum Coefficients. Both the training and synthesis issues a...

The Bonn Open Synthesis System (BOSS) is open-source software for unit selection speech synthesis that has been used for the generation of high-quality German and Dutch speech. This article presents ongoing research and development aimed at adapting BOSS to the Polish language. In the first section, the origins and workings of the unit selection method for speech synthesis are explained. Sectio...

In this paper we discuss various digital filter principles as models for synthetic speech generation. Warped linear prediction (WLP) and frequency-warped filters have been introduced earlier as a method to reduce the filter order in high-quality wideband speech synthesis. In addition to analyzing WLP and frequency-warped filters we introduce new related structures and techniques for arbitrary f...

In control vector-based expressive speech synthesis, the emotion/style control vector defined in the categorical (CAT) emotion space is uneasy to be precisely defined by the user to synthesize the speech with the desired emotion/style. This paper applies the arousal-valence (AV) space to the multiple regression hidden semi-Markov model (MRHSMM)-based synthesis framework for expressive speech sy...

A concatenative speech synthesis system increases its potential to generate natural speech if the system uses more short speech segments, since the concatenation variation becomes greater. In this paper, we propose the use of very short speech segments (5 ms, one pitch period of 200 Hz pitch) for concatenative speech synthesis. The proposed method is applied to the speech database CMU ARCTIC, a...

This paper describes the modeling of various emotional expressions and speaking styles in synthetic speech using HMM-based speech synthesis. We show two methods for modeling speaking styles and emotional expressions. In the first method called style-dependent modeling, each speaking style and emotional expression is modeled individually. In the second one called style-mixed modeling, each speak...

The Bonn Open Synthesis System (BOSS) is an open-source software for the unit selection speech synthesis that has been used for the generation of high-quality German and Dutch speech. This article presents ongoing research and development aimed at adapting BOSS to the Polish language. In the first section, the origins and workings of the unit selection method for speech synthesis are explained....