The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
O parâmetro de envelope espectral é um parâmetro de fala significativo na qualidade do vocoder. Recentemente, o Vector Quantized Variational AutoEncoder (VQ-VAE) é um método de quantização ponta a ponta de última geração baseado no modelo de aprendizagem profunda. Este artigo propôs uma nova técnica para melhorar a incorporação da aprendizagem espacial do VQ-VAE com a Rede Adversarial Generativa para quantizar o parâmetro do envelope espectral, chamada VQ-VAE-EMGAN. Em experimentos, projetamos o quantizador para os parâmetros do envelope espectral do vocoder WORLD extraído da forma de onda da fala de 16kHz. Conforme os resultados mostrados, a técnica proposta reduziu a Distorção Espectral Log (LSD) em torno de 0.5dB e aumentou o PESQ em cerca de 0.17 em média para operações de quatro bits alvo em comparação com o VQ-VAE convencional.
Tanasan SRIKOTR
Shibaura Institute of Technology
Kazunori MANO
Shibaura Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Tanasan SRIKOTR, Kazunori MANO, "Vector Quantization of Speech Spectrum Based on the VQ-VAE Embedding Space Learning by GAN Technique" in IEICE TRANSACTIONS on Fundamentals,
vol. E105-A, no. 4, pp. 647-654, April 2022, doi: 10.1587/transfun.2021SMP0018.
Abstract: The spectral envelope parameter is a significant speech parameter in the vocoder's quality. Recently, the Vector Quantized Variational AutoEncoder (VQ-VAE) is a state-of-the-art end-to-end quantization method based on the deep learning model. This paper proposed a new technique for improving the embedding space learning of VQ-VAE with the Generative Adversarial Network for quantizing the spectral envelope parameter, called VQ-VAE-EMGAN. In experiments, we designed the quantizer for the spectral envelope parameters of the WORLD vocoder extracted from the 16kHz speech waveform. As the results shown, the proposed technique reduced the Log Spectral Distortion (LSD) around 0.5dB and increased the PESQ by around 0.17 on average for four target bit operations compared to the conventional VQ-VAE.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2021SMP0018/_p
Copiar
@ARTICLE{e105-a_4_647,
author={Tanasan SRIKOTR, Kazunori MANO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Vector Quantization of Speech Spectrum Based on the VQ-VAE Embedding Space Learning by GAN Technique},
year={2022},
volume={E105-A},
number={4},
pages={647-654},
abstract={The spectral envelope parameter is a significant speech parameter in the vocoder's quality. Recently, the Vector Quantized Variational AutoEncoder (VQ-VAE) is a state-of-the-art end-to-end quantization method based on the deep learning model. This paper proposed a new technique for improving the embedding space learning of VQ-VAE with the Generative Adversarial Network for quantizing the spectral envelope parameter, called VQ-VAE-EMGAN. In experiments, we designed the quantizer for the spectral envelope parameters of the WORLD vocoder extracted from the 16kHz speech waveform. As the results shown, the proposed technique reduced the Log Spectral Distortion (LSD) around 0.5dB and increased the PESQ by around 0.17 on average for four target bit operations compared to the conventional VQ-VAE.},
keywords={},
doi={10.1587/transfun.2021SMP0018},
ISSN={1745-1337},
month={April},}
Copiar
TY - JOUR
TI - Vector Quantization of Speech Spectrum Based on the VQ-VAE Embedding Space Learning by GAN Technique
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 647
EP - 654
AU - Tanasan SRIKOTR
AU - Kazunori MANO
PY - 2022
DO - 10.1587/transfun.2021SMP0018
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E105-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 2022
AB - The spectral envelope parameter is a significant speech parameter in the vocoder's quality. Recently, the Vector Quantized Variational AutoEncoder (VQ-VAE) is a state-of-the-art end-to-end quantization method based on the deep learning model. This paper proposed a new technique for improving the embedding space learning of VQ-VAE with the Generative Adversarial Network for quantizing the spectral envelope parameter, called VQ-VAE-EMGAN. In experiments, we designed the quantizer for the spectral envelope parameters of the WORLD vocoder extracted from the 16kHz speech waveform. As the results shown, the proposed technique reduced the Log Spectral Distortion (LSD) around 0.5dB and increased the PESQ by around 0.17 on average for four target bit operations compared to the conventional VQ-VAE.
ER -