ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing
DOI: 10.1109/icassp.1988.196672
|View full text |Cite
|
Sign up to set email alerts
|

Automatic generation of synthesis units based on context oriented clustering

Abstract: This paper proposes a new text-to-speech synthesis method based on automatic synthesis unit generation techniques using natural speech database. We have termed the text Oriented Clustering (COC). e, 627 phonetic synthesis units were generated automatically based on 432 words uttered by a male speaker. This systematic approach has several advantages. First, as synthesis units can be generated ically without any a priori phonological knowledge, sy to change the number of units and voices. Second, following from … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
17
0
2

Publication Types

Select...
8
2

Relationship

0
10

Authors

Journals

citations
Cited by 48 publications
(19 citation statements)
references
References 6 publications
0
17
0
2
Order By: Relevance
“…During synthesis, pitch and duration modification are used to obtain a desired prosody. Unit selection synthesis is the most popular variant of concatenative synthesis, and was first proposed by Nakajama and Hamada in 1988 [26]. Since then various systems including commercial systems were developed resulting in a higher level of reading-style synthetic speech [27,28,29] and it is today considered as the state of the art in text-to speech synthesis.…”
Section: Fig 4 Architecture Of a Concatenative Text-to-speech Systemmentioning
confidence: 99%
“…During synthesis, pitch and duration modification are used to obtain a desired prosody. Unit selection synthesis is the most popular variant of concatenative synthesis, and was first proposed by Nakajama and Hamada in 1988 [26]. Since then various systems including commercial systems were developed resulting in a higher level of reading-style synthetic speech [27,28,29] and it is today considered as the state of the art in text-to speech synthesis.…”
Section: Fig 4 Architecture Of a Concatenative Text-to-speech Systemmentioning
confidence: 99%
“…pitch and duration modification are used to obtain a desired prosody. Unit selection synthesis is the most popular variant of concatenative synthesis and was first proposed by Nakajama and Hamada in 1988 [15]. Since then various systems including commercial systems were developed resulting in a higher level of reading-style synthetic speech [16,17,18] and it is today considered as the state of art in text-to speech synthesis.…”
Section: Fig 1: Block Diagram Of General Text To Speech Systemmentioning
confidence: 99%
“…Special methods to generate a unit inventory have been proposed by the research group at NTT in Japan (10,11). The synthesis allophones are selected with the help of the contextoriented clustering (COC) method.…”
Section: Concatenation Of Unitsmentioning
confidence: 99%