预测矢量量化变分自编码器的频谱包络量化

2020 International Conference on Electronics, Information, and Communication (ICEIC) Pub Date : 2020-01-01 DOI:10.1109/ICEIC49074.2020.9051233

Tanasan Srikotr, K. Mano

{"title":"预测矢量量化变分自编码器的频谱包络量化","authors":"Tanasan Srikotr, K. Mano","doi":"10.1109/ICEIC49074.2020.9051233","DOIUrl":null,"url":null,"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.","PeriodicalId":271345,"journal":{"name":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Predictive Vector Quantized Variational AutoEncoder for Spectral Envelope Quantization\",\"authors\":\"Tanasan Srikotr, K. Mano\",\"doi\":\"10.1109/ICEIC49074.2020.9051233\",\"DOIUrl\":null,\"url\":null,\"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.\",\"PeriodicalId\":271345,\"journal\":{\"name\":\"2020 International Conference on Electronics, Information, and Communication (ICEIC)\",\"volume\":\"38 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 International Conference on Electronics, Information, and Communication (ICEIC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICEIC49074.2020.9051233\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICEIC49074.2020.9051233","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

为了改善传统的VQ-VAE重构误差，提出了预测向量量化变分自编码器。该模型可以根据以前的数据预测当前的数据。对高质量48khz WORLD声码器量化谱包络参数的性能进行了评价。结果表明，与传统的VQ-VAE相比，预测矢量量化变分自编码器在4个目标比特率下具有较低的对数谱失真。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Predictive Vector Quantized Variational AutoEncoder for Spectral Envelope Quantization

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.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2020 International Conference on Electronics, Information, and Communication (ICEIC)

自引率

0.00%

发文量