Speech analysis-synthesis system and quality of synthesized speech using mel-cepstrum

1986 ◽  
Vol 69 (10) ◽  
pp. 47-54 ◽  
Author(s):  
Tadashi Kitamura ◽  
Satoshi Imai ◽  
Chieko Furuichi ◽  
Takao Kobayashi
Keyword(s):  
Speech Analysis ◽  
Synthesis System ◽  
Synthesized Speech ◽  
Mel Cepstrum

Di-Diphone Arabic Speech Synthesis Concatenation

2012 ◽  
Vol 3 (2) ◽  
pp. 218-222 ◽  
Author(s):  
Abdelkader Chabchoub ◽  
Salah Alahmadi ◽  
Adnan Cherif ◽  
Wahid Barkouti
Keyword(s):  
Speech Synthesis ◽  
Arabic Text ◽  
Text To Speech ◽  
Synthesis System ◽  
Voice Source ◽  
Synthesized Speech ◽  
Different Types ◽  
The Voice

This work describes the new Arabic Text-to-speech (TTS) synthesis system. This system based on di-Diphone concatenation with TD-PSOLA modifier synthesizer. The quality of a synthesized speech is improved by analyzing the spectrum features of voice source in various F0 ranges and timbres in detail and new unites concatenation. It generates speech synthesis based on analysis and estimation of formant by classifying the voice source into different types. The developed model enhances the quality of the naturalness, and the intelligibility of speech synthesis in various speaking environment.

Unit-Selection Speech Synthesis Method Using Words as Search Units

2016 ◽  
Vol 7 (2) ◽  
pp. 53-67
Author(s):  
Hiroyuki Segi
Keyword(s):  
Conventional Method ◽  
Speech Synthesis ◽  
Synthesis Method ◽  
Unit Selection ◽  
Human Speech ◽  
Subjective Evaluations ◽  
Synthesized Speech ◽  
Opinion Score ◽  
Speech Database

Unit-selection speech-synthesis systems have been proposed. In most of the unit-selection speech-synthesis systems, search units are rather short such as syllables, phonemes and diphones. However, when applied to large speech databases, shorter units produce more voice-waveform candidates and a larger speech database cannot be used without narrow pruning for practical use. Narrow pruning impairs the quality of the synthesized speech. Here the author examined the possibility of using words as search units. Subjective evaluations indicated that 70% of the speech synthesized by the proposed method sounded more natural than that synthesized by a conventional method. The five-point mean opinion score of the synthesized speech was 3.5, and 21% was judged to sound as natural as human speech. These results demonstrate the effectiveness of unit-selection speech synthesis using words as search units.

Speech quality evaluation for different pitch detection algorithms in LPC speech analysis–synthesis system

2020 ◽  
Author(s):  
Sandeep Kumar ◽  
Sneha Singh ◽  
Prabhakar Agarwal ◽  
Upendra Kumar Acharya ◽  
Prabira Kumar Sethy ◽  
...  
Keyword(s):  
Quality Evaluation ◽  
Speech Quality ◽  
Speech Analysis ◽  
Pitch Detection ◽  
Synthesis System ◽  
Detection Algorithms

Formant tracking algorithm for a speech analysis‐synthesis system

1975 ◽  
Vol 58 (S1) ◽  
pp. S23-S23
Author(s):  
P. M. Seeviour ◽  
J. N. Holmes ◽  
M. W. Judd
Keyword(s):  
Tracking Algorithm ◽  
Speech Analysis ◽  
Synthesis System ◽  
Formant Tracking

SOFTWARE SYNTHESIS SHELL SOFTEXSHELL AND ITS APPLICATION TO SWITCHING SERVICE SOFTWARE

1996 ◽  
Vol 05 (03) ◽  
pp. 291-304
Author(s):  
TORU YAMANOUCHI ◽  
AKIYOSHI SATO ◽  
MASANOBU WATANABE ◽  
HIROYUKI WATANABE ◽  
HIROMITSU YAMANAKA
Keyword(s):  
Term Rewriting ◽  
Software Synthesis ◽  
Synthesis System ◽  
Prototype Development ◽  
Transformation Rules ◽  
System A ◽  
Software Model ◽  
Software Engineers ◽  
Efficient Software

To improve the productivity and quality of software development, a software synthesis shell called SOFTEXSHELL has been developed. SOFTEXSHELL is a tool kit with a transformation system based on a term rewriting system, a language DSL/C++ for defining transformation rules as well as a specification language for a specific software model, and a rule verification system which supports development of correct transformation rules. The system is designed to provide an environment which enables a broad range of software engineers to construct software synthesis systems for their domains. To evaluate how effectively SOFTEXSHELL does this, a software synthesis system for switching scenario software was developed by two switching software specialists without prior software synthesis experience. After a four-month prototype development period, a practical software synthesis system for switching service software was developed in eight months. The developed software synthesis system, SOFTEX/EX, has been utilized for developing six switching systems. Generated programs, including 272,000 steps in total, have been in daily operation. Based on the development process and developed system results, we conclude that SOFTEXSHELL enables software engineers, without prior software synthesis experience, to develop useful and efficient software synthesis systems.

scholarly journals Synthesis of Human Voice Fragments Based on Frequency Spectra Reconstruction

2021 ◽  
Vol 24 (2) ◽  
pp. 14-20
Author(s):  
G. Lan ◽  
◽  
A. S. Fadeev ◽  
A. N. Morgunov ◽  
◽  
...  
Keyword(s):  
Speech Signal ◽  
Analytical Description ◽  
Frequency Characteristics ◽  
Frequency Spectra ◽  
Human Voice ◽  
Synthesized Speech

This article details the development of methods for the synthesis of phonemes of the human voice based on the analytical description of individual formants. A technique for analyzing the spectrum and spectrograms of original phonemes to obtain the main amplitude-frequency characteristics of the signal components is presented. An algorithm to reconstruct a speech signal based on the obtained sets of parameters is proposed. A technique to assess the quality of synthesized speech elements is described

Sign in / Sign up

Export Citation Format

Share Document