Predictive vector quantized variational autoencoder for spectral envelope quantization

Tanasan Srikotr, Kazunori Mano

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
出版ステータスPublished - 2020 1
イベント2020 International Conference on Electronics, Information, and Communication, ICEIC 2020 - Barcelona, Spain
継続期間: 2020 1 192020 1 22

出版物シリーズ

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

Conference

Conference2020 International Conference on Electronics, Information, and Communication, ICEIC 2020
CountrySpain
CityBarcelona
Period20/1/1920/1/22

ASJC Scopus subject areas

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

フィンガープリント 「Predictive vector quantized variational autoencoder for spectral envelope quantization」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル