@inproceedings{tao-etal-2024-fast-high,
title = "A Fast and High-quality Text-to-Speech Method with Compressed Auxiliary Corpus and Limited Target Speaker Corpus",
author = "Tao, Ye and
Lu, Chaofeng and
Liu, Meng and
Xu, Kai and
Liu, Tianyu and
Tian, Yunlong and
Du, Yongjie",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.46",
pages = "525--535",
abstract = "With an auxiliary corpus (non-target speaker corpus) for model pre-training, Text-to-Speech (TTS) methods can generate high-quality speech with a limited target speaker corpus. However, this approach comes with expensive training costs. To overcome the challenge, a high-quality TTS method is proposed, significantly reducing training costs while maintaining the naturalness of synthesized speech. In this paper, we propose an auxiliary corpus compression algorithm that reduces the training cost while the naturalness of the synthesized speech is not significantly degraded. We then use the compressed corpus to pre-train the proposed TTS model CMDTTS, which fuses phoneme and word multi-level prosody modeling components and denoises the generated mel-spectrograms using denoising diffusion probabilistic models (DDPMs). In addition, a fine-tuning step that the conditional generative adversarial network (cGAN) is introduced to embed the target speaker feature and improve speech quality using the target speaker corpus. Experiments are conducted on Chinese and English single speaker{'}s corpora, and the results show that the method effectively balances the model training speed and the synthesized speech quality and outperforms the current models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tao-etal-2024-fast-high">
<titleInfo>
<title>A Fast and High-quality Text-to-Speech Method with Compressed Auxiliary Corpus and Limited Target Speaker Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaofeng</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunlong</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjie</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With an auxiliary corpus (non-target speaker corpus) for model pre-training, Text-to-Speech (TTS) methods can generate high-quality speech with a limited target speaker corpus. However, this approach comes with expensive training costs. To overcome the challenge, a high-quality TTS method is proposed, significantly reducing training costs while maintaining the naturalness of synthesized speech. In this paper, we propose an auxiliary corpus compression algorithm that reduces the training cost while the naturalness of the synthesized speech is not significantly degraded. We then use the compressed corpus to pre-train the proposed TTS model CMDTTS, which fuses phoneme and word multi-level prosody modeling components and denoises the generated mel-spectrograms using denoising diffusion probabilistic models (DDPMs). In addition, a fine-tuning step that the conditional generative adversarial network (cGAN) is introduced to embed the target speaker feature and improve speech quality using the target speaker corpus. Experiments are conducted on Chinese and English single speaker’s corpora, and the results show that the method effectively balances the model training speed and the synthesized speech quality and outperforms the current models.</abstract>
<identifier type="citekey">tao-etal-2024-fast-high</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.46</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>525</start>
<end>535</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Fast and High-quality Text-to-Speech Method with Compressed Auxiliary Corpus and Limited Target Speaker Corpus
%A Tao, Ye
%A Lu, Chaofeng
%A Liu, Meng
%A Xu, Kai
%A Liu, Tianyu
%A Tian, Yunlong
%A Du, Yongjie
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F tao-etal-2024-fast-high
%X With an auxiliary corpus (non-target speaker corpus) for model pre-training, Text-to-Speech (TTS) methods can generate high-quality speech with a limited target speaker corpus. However, this approach comes with expensive training costs. To overcome the challenge, a high-quality TTS method is proposed, significantly reducing training costs while maintaining the naturalness of synthesized speech. In this paper, we propose an auxiliary corpus compression algorithm that reduces the training cost while the naturalness of the synthesized speech is not significantly degraded. We then use the compressed corpus to pre-train the proposed TTS model CMDTTS, which fuses phoneme and word multi-level prosody modeling components and denoises the generated mel-spectrograms using denoising diffusion probabilistic models (DDPMs). In addition, a fine-tuning step that the conditional generative adversarial network (cGAN) is introduced to embed the target speaker feature and improve speech quality using the target speaker corpus. Experiments are conducted on Chinese and English single speaker’s corpora, and the results show that the method effectively balances the model training speed and the synthesized speech quality and outperforms the current models.
%U https://aclanthology.org/2024.lrec-main.46
%P 525-535
Markdown (Informal)
[A Fast and High-quality Text-to-Speech Method with Compressed Auxiliary Corpus and Limited Target Speaker Corpus](https://aclanthology.org/2024.lrec-main.46) (Tao et al., LREC-COLING 2024)
ACL
- Ye Tao, Chaofeng Lu, Meng Liu, Kai Xu, Tianyu Liu, Yunlong Tian, and Yongjie Du. 2024. A Fast and High-quality Text-to-Speech Method with Compressed Auxiliary Corpus and Limited Target Speaker Corpus. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 525–535, Torino, Italia. ELRA and ICCL.