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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.

Original language	English
Title of host publication	2020 International Conference on Electronics, Information, and Communication, ICEIC 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728162898
DOIs	https://doi.org/10.1109/ICEIC49074.2020.9051233
Publication status	Published - 2020 Jan
Event	2020 International Conference on Electronics, Information, and Communication, ICEIC 2020 - Barcelona, Spain Duration: 2020 Jan 19 → 2020 Jan 22

Publication series

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

Conference

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

Keywords

Predictive vector quantization
Spectral envelope
Vector quantized variational autoencoder
WORLD vocoder

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Hardware and Architecture
Information Systems and Management
Electrical and Electronic Engineering

Access to Document

10.1109/ICEIC49074.2020.9051233

Cite this

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).

Research output: Chapter in Book/Report/Conference proceeding › 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

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this