Proceedings ArticleDOI
An application of the linear prediction technique to efficient coding of speech segments
G. Mian,F. Morgantini,C. Offelli +2 more
- Vol. 1, pp 722-722
TLDR
The quantitative rules obtained for generating the SSRU's are expected to be useful, at least as a preliminary investigation tool, for synthesis-by-rule.Abstract:
Summary form only given, as follows. The paper deals with the application of linear prediction technique to the speech synthesis of both italian and german languages by Standard Speech Reproducing Units (SSRU), it is by combining elementary speech segments of standardized charac teristics extracted fron utterances of native speakers. The nain feature of the method presented is the possibility of synthesizing in a higly intelligible form any nessage of such languages with a very limited amount of data. So far the use of linear predictive coding of the previously realized SSRU sets allowed a memory occupation less than 16 kb for the synthesis of italian language and less than 32 k-bytes for the combined synthesis of italian and german languages. The data flow rate is about 1 kb/s. A key property of the code with respect to methods previously used (i.e. simple concatenation of original segments ) relies in the possibility of greatly enhancing the naturalness of the synthesized speech by varying pitch, amplitude and duration of the synthetic segments. Further, the quantitative rules obtained for generating the SSRU's are expected to be useful, at least as a preliminary investigation tool, for synthesis-by-rule.read more
Citations
More filters
Book
Development of electronic aids for the visually impaired : proceedings of a Workshop on the Rehabilitation of the Visually Impaired, held at the Institute for Research on Electromagnetic Waves of the National Research Council, Florence, Italy
TL;DR: The Elekul Braille System as mentioned in this paper is a Braille text processing system for the blind in the German Federal Republic of Germany with the purpose of providing written communication aid between sighted and non-sighted persons.
Proceedings ArticleDOI
A technique for converting the linear prediction areas model of speech to a simple articulatory model
S. Brooks,F. Fallside +1 more
TL;DR: The transform has been implemented in a real-time articulatory display which gives an overhead of only 14% over simple linear prediction area extraction and was found to be capable of showing the position of any vowel.
Book ChapterDOI
Synthesis of Greek Speech with Elementary Speech Segments
TL;DR: Computer-synthesis of Greek speech has been performed by combining elementary speech segments, extracted from the utterances of a Greek speaker and stored in a digital computer, and the method in order to improve the intelligibility and the naturalness of the synthetic speech is described.
The UOP text-to-speech system for Greek speech synthesis.
TL;DR: The Greek TTS synthesizer uses waveform unit concatenation technology working with a sophisticated speech database and produces good quality speech synthesis of the Greek language.
Related Papers (5)
Robust Automatic Continuous Speech Segmentation for Indian Languages to Improve Speech to Speech Translation
J. Sangeetha,S. Jothilakshmi +1 more
Unit selection in a concatenative speech synthesis system using a large speech database
Andrew Hunt,Alan W. Black +1 more