Paraphrase generation to improve Text-To-Speech Synthesis

被引：0

作者：

Putois, Ghislain ^{[1
]}

Chevelu, Jonathan ^{[1
]}

Boidin, Cedric ^{[1
]}

机构：

[1] Orange Labs, Lannion, France

来源：

11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2 | 2010年

关键词：

speech synthesis; statistical paraphrase; unit selection; synthesis costs; Europarl;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Text-to-speech synthesizer systems are of overall good quality, especially when adapted to a specific task. Given this task and an adapted voice corpus, the message quality is mainly dependent on the wording used. This paper presents how a paraphrase generator can be used in synergy with a text-to-speech (TTs) synthesis system to improve its overall performances. Our system is composed of a paraphrase generator using a French-to-French corpus learnt on a bilingual aligned corpus, a TTS selector based on the unit selection cost, and a TTS synthesizer. We present an evaluation of the system, which highlights the need for systematic subjective evaluation.

引用

页码：198 / 201

页数：4

共 50 条

[1] TEXT-TO-SPEECH SYNTHESIS
SPROAT, RW
OLIVE, JP
[J]. AT&T TECHNICAL JOURNAL, 1995, 74 (02): : 35 - 44
[2] Combining conversational speech with read speech to improve prosody in Text-to-Speech synthesis
O'Mahony, Johannah
Lai, Catherine
King, Simon
[J]. INTERSPEECH 2022, 2022, : 3388 - 3392
[3] Text and Speech Corpora for Text-To-Speech Synthesis of Tales
Doukhan, David
Rosset, Sophie
Rilliard, Albert
d'Alessandro, Christophe
Adda-Decker, Martine
[J]. LREC 2012 - EIGHTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2012, : 1003 - 1010
[4] Multilingual text-to-speech synthesis
Black, AW
Lenzo, KA
[J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL III, PROCEEDINGS: IMAGE AND MULTIDIMENSIONAL SIGNAL PROCESSING SPECIAL SESSIONS, 2004, : 761 - 764
[5] An introduction to text-to-speech synthesis
Fitzpatrick, E
[J]. COMPUTATIONAL LINGUISTICS, 1998, 24 (02) : 322 - 323
[6] Improving text-to-speech synthesis
Tatham, M
Lewis, E
[J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 1856 - 1859
[7] Issues in text-to-speech synthesis
Macchi, M
[J]. IEEE INTERNATIONAL JOINT SYMPOSIA ON INTELLIGENCE AND SYSTEMS - PROCEEDINGS, 1998, : 318 - 325
[8] Automatic generation of synthesis units for trainable text-to-speech systems
Hon, H
Acero, A
Huang, X
Liu, J
Plumpe, M
[J]. PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 293 - 296
[9] Multilingual text analysis for text-to-speech synthesis
Sproat, R
[J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 1365 - 1368
[10] PARAMETER GENERATION ALGORITHMS FOR TEXT-TO-SPEECH SYNTHESIS WITH RECURRENT NEURAL NETWORKS
Klimkov, Viacheslav
Moinet, Alexis
Nadolski, Adam
Drugman, Thomas
[J]. 2018 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2018), 2018, : 626 - 631

← 1 2 3 4 5 →