scholarly journals Formant characteristics of Malay vowels

2020 ◽  
Vol 9 (1) ◽  
pp. 144
Author(s):  
Izzad Ramli ◽  
Nursuriati Jamil ◽  
Norizah Ardi
Keyword(s):  
Speech Synthesis ◽  
Front Vowel ◽  
International Phonetic Alphabet ◽  
Interactive Editing ◽  
Speech Rehabilitation ◽  
Degree Of Overlap

The purpose of this study was to investigate and examined the eight vowels formant characteristic of Malay language. Previous research of Malay language only investigated six basic vowels /a/, /e/, /i/, /o/, /u/, /ə/. The vowels /ɔ/, /ε/ that usually exist in a dialect were not included in the previous investigations. In this study, the vowels sound were collected from five men and four women producing the vowels /a/, /e/, /i/, /o/, /u/, /ə/, /ɔ/, /ε/ from different regions and dialects in Malaysia. Formant contours, F1 until F4 of the vowels were measured using interactive editing tool called Praat. Analysis of the formant data showed numerous differences between vowels in terms of average frequencies of F1 and F2, and the degree of overlap among adjacent vowels. When compared with the International Phonetic Alphabet (IPA), most pronunciation of the Malay vowels were at the same position but the vowel /ε/ seen more likely to become a front vowel instead of a central vowel. Consequently, vowel features of the two Malay allophones /ɔ/ and /ε/ were documented and added to the IPA vowel chart. The findings form the fundamental basis for further research of speech synthesis, speech rehabilitation and speech reproduction of the Malay language.

Speech synthesis from natural models by hand and by algorithm

2009 ◽  
Author(s):  
Robert E. Remez ◽  
Kathryn R. Dubowski ◽  
Morgana L. Davids ◽  
Emily F. Thomas ◽  
Nina Paddu ◽  
...  
Keyword(s):  
Speech Synthesis

Design of English text-to-speech conversion algorithm based on machine learning

2020 ◽  
pp. 1-12
Author(s):  
Li Dongmei
Keyword(s):  
Machine Learning ◽  
Speech Synthesis ◽  
Feature Recognition ◽  
Learning Algorithm ◽  
Morphological Structure ◽  
English Text ◽  
Text To Speech ◽  
Part Of Speech ◽  
Modern Computer ◽  
Conversion Algorithm

English text-to-speech conversion is the key content of modern computer technology research. Its difficulty is that there are large errors in the conversion process of text-to-speech feature recognition, and it is difficult to apply the English text-to-speech conversion algorithm to the system. In order to improve the efficiency of the English text-to-speech conversion, based on the machine learning algorithm, after the original voice waveform is labeled with the pitch, this article modifies the rhythm through PSOLA, and uses the C4.5 algorithm to train a decision tree for judging pronunciation of polyphones. In order to evaluate the performance of pronunciation discrimination method based on part-of-speech rules and HMM-based prosody hierarchy prediction in speech synthesis systems, this study constructed a system model. In addition, the waveform stitching method and PSOLA are used to synthesize the sound. For words whose main stress cannot be discriminated by morphological structure, label learning can be done by machine learning methods. Finally, this study evaluates and analyzes the performance of the algorithm through control experiments. The results show that the algorithm proposed in this paper has good performance and has a certain practical effect.

Milvia Bollati, Flora Cassen, and Marc Michael Epstein, The Lombard Haggadah. Introduction by Christopher de Hamel. Ed. Sandra Hindman. Les Eluminures. New York: Paul Holberton, 2019, 239 pp., colored ill.

Mediaevistik ◽  
2020 ◽  
Vol 32 (1) ◽  
pp. 509-511
Author(s):  
Albrecht Classen
Keyword(s):  
New York ◽  
Considerable Degree ◽  
Illustrated Manuscripts ◽  
Public Display ◽  
Manuscript Production ◽  
Privately Owned ◽  
Degree Of Overlap

Those of us who work with medieval illustrated manuscripts are often guilty of ignoring the major contributions by medieval Jewish scribes and illuminators or the manuscripts produced for Jewish consumers. To remedy this situation, Milivia Bollati, Flora Cassen, and Marc Michael Epstein here present the most impressive Lombard Haggadah, both by examining its background, purpose, design, and by providing a complete facsimile of the manuscript. Famous Christopher de Hamel (Cambridge) adds a pleasant introduction in which he emphasizes the considerable degree of overlap of Christian and Jewish manuscript production. The Lombard Haggadah is the earliest stand-alone Haggadah and is one of only three illustrated medieval Haggadot still privately owned (Sandra Hindman, 8). This manuscript was on public display in New York in April 2019, and was for sale. <?page nr="510"?>It is not clear to me whether any buyer acquired it.

Integrating Articulatory Information in Deep Learning-Based Text-to-Speech Synthesis

2017 ◽  
Author(s):  
Beiming Cao ◽  
Myungjong Kim ◽  
Jan van Santen ◽  
Ted Mau ◽  
Jun Wang
Keyword(s):  
Deep Learning ◽  
Speech Synthesis ◽  
Text To Speech ◽  
Text To Speech Synthesis
Sign in / Sign up

Export Citation Format

Share Document