Predictive vector quantized variational autoencoder for spectral envelope quantization

Tanasan Srikotr; Kazunori Mano

doi:10.1109/ICEIC49074.2020.9051233

Predictive vector quantized variational autoencoder for spectral envelope quantization

研究成果: Conference contribution

抄録

The Predictive Vector Quantized Variational AutoEncoder is proposed to improve the reconstruction error of the conventional VQ-VAE. The proposed model can predict the current data from the previous data. The performance of the quantized spectral envelope parameters of the high-quality 48 kHz WORLD vocoder is evaluated. The results indicate that the Predictive Vector Quantized Variational AutoEncoder has a lower distortion with four target bitrates in term of log-spectral distortion, compared with the conventional VQ-VAE.

本文言語	English
ホスト出版物のタイトル	2020 International Conference on Electronics, Information, and Communication, ICEIC 2020
出版社	Institute of Electrical and Electronics Engineers Inc.
ISBN（電子版）	9781728162898
DOI	https://doi.org/10.1109/ICEIC49074.2020.9051233
出版ステータス	Published - 2020 1月
イベント	2020 International Conference on Electronics, Information, and Communication, ICEIC 2020 - Barcelona, Spain 継続期間: 2020 1月 19 → 2020 1月 22

出版物シリーズ

名前	2020 International Conference on Electronics, Information, and Communication, ICEIC 2020

Conference

Conference	2020 International Conference on Electronics, Information, and Communication, ICEIC 2020
国/地域	Spain
City	Barcelona
Period	20/1/19 → 20/1/22

ASJC Scopus subject areas

コンピュータネットワークおよび通信
コンピュータサイエンスの応用
ハードウェアとアーキテクチャ
情報システムおよび情報管理
電子工学および電気工学

文献へのアクセス

10.1109/ICEIC49074.2020.9051233

他のファイルとリンク

引用スタイル

Srikotr, T., & Mano, K. (2020). Predictive vector quantized variational autoencoder for spectral envelope quantization. In 2020 International Conference on Electronics, Information, and Communication, ICEIC 2020 [9051233] (2020 International Conference on Electronics, Information, and Communication, ICEIC 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICEIC49074.2020.9051233

Predictive vector quantized variational autoencoder for spectral envelope quantization. / Srikotr, Tanasan; Mano, Kazunori.
2020 International Conference on Electronics, Information, and Communication, ICEIC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9051233 (2020 International Conference on Electronics, Information, and Communication, ICEIC 2020).

研究成果: Conference contribution

Srikotr, T & Mano, K 2020, Predictive vector quantized variational autoencoder for spectral envelope quantization. in 2020 International Conference on Electronics, Information, and Communication, ICEIC 2020., 9051233, 2020 International Conference on Electronics, Information, and Communication, ICEIC 2020, Institute of Electrical and Electronics Engineers Inc., 2020 International Conference on Electronics, Information, and Communication, ICEIC 2020, Barcelona, Spain, 20/1/19. https://doi.org/10.1109/ICEIC49074.2020.9051233

Srikotr T, Mano K. Predictive vector quantized variational autoencoder for spectral envelope quantization. In 2020 International Conference on Electronics, Information, and Communication, ICEIC 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9051233. (2020 International Conference on Electronics, Information, and Communication, ICEIC 2020). doi: 10.1109/ICEIC49074.2020.9051233

@inproceedings{ab009c91842947438efd5bbd376b88ab,

title = "Predictive vector quantized variational autoencoder for spectral envelope quantization",

abstract = "The Predictive Vector Quantized Variational AutoEncoder is proposed to improve the reconstruction error of the conventional VQ-VAE. The proposed model can predict the current data from the previous data. The performance of the quantized spectral envelope parameters of the high-quality 48 kHz WORLD vocoder is evaluated. The results indicate that the Predictive Vector Quantized Variational AutoEncoder has a lower distortion with four target bitrates in term of log-spectral distortion, compared with the conventional VQ-VAE.",

keywords = "Predictive vector quantization, Spectral envelope, Vector quantized variational autoencoder, WORLD vocoder",

author = "Tanasan Srikotr and Kazunori Mano",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 International Conference on Electronics, Information, and Communication, ICEIC 2020 ; Conference date: 19-01-2020 Through 22-01-2020",

year = "2020",

month = jan,

doi = "10.1109/ICEIC49074.2020.9051233",

language = "English",

series = "2020 International Conference on Electronics, Information, and Communication, ICEIC 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 International Conference on Electronics, Information, and Communication, ICEIC 2020",

}

TY - GEN

T1 - Predictive vector quantized variational autoencoder for spectral envelope quantization

AU - Srikotr, Tanasan

AU - Mano, Kazunori

PY - 2020/1

Y1 - 2020/1

N2 - The Predictive Vector Quantized Variational AutoEncoder is proposed to improve the reconstruction error of the conventional VQ-VAE. The proposed model can predict the current data from the previous data. The performance of the quantized spectral envelope parameters of the high-quality 48 kHz WORLD vocoder is evaluated. The results indicate that the Predictive Vector Quantized Variational AutoEncoder has a lower distortion with four target bitrates in term of log-spectral distortion, compared with the conventional VQ-VAE.

AB - The Predictive Vector Quantized Variational AutoEncoder is proposed to improve the reconstruction error of the conventional VQ-VAE. The proposed model can predict the current data from the previous data. The performance of the quantized spectral envelope parameters of the high-quality 48 kHz WORLD vocoder is evaluated. The results indicate that the Predictive Vector Quantized Variational AutoEncoder has a lower distortion with four target bitrates in term of log-spectral distortion, compared with the conventional VQ-VAE.

KW - Predictive vector quantization

KW - Spectral envelope

KW - Vector quantized variational autoencoder

KW - WORLD vocoder

UR - http://www.scopus.com/inward/record.url?scp=85083512835&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85083512835&partnerID=8YFLogxK

U2 - 10.1109/ICEIC49074.2020.9051233

DO - 10.1109/ICEIC49074.2020.9051233

M3 - Conference contribution

AN - SCOPUS:85083512835

T3 - 2020 International Conference on Electronics, Information, and Communication, ICEIC 2020

BT - 2020 International Conference on Electronics, Information, and Communication, ICEIC 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 International Conference on Electronics, Information, and Communication, ICEIC 2020

Y2 - 19 January 2020 through 22 January 2020

ER -

Predictive vector quantized variational autoencoder for spectral envelope quantization

抄録

出版物シリーズ

Conference

ASJC Scopus subject areas

文献へのアクセス

他のファイルとリンク

フィンガープリント

引用スタイル