Wav2wav: Wave-to-Wave Voice Conversion

Author:

Jeong Changhyeon1ORCID,Chang Hyung-pil2,Yoo In-Chul2ORCID,Yook Dongsuk2

Affiliation:

1. Lotte Innovate Co., Ltd., Seoul 08500, Republic of Korea

2. Artificial Intelligence Laboratory, Department of Computer Science and Engineering, Korea University, Seoul 02841, Republic of Korea

Abstract

Voice conversion is the task of changing the speaker characteristics of input speech while preserving its linguistic content. It can be used in various areas, such as entertainment, medicine, and education. The quality of the converted speech is crucial for voice conversion algorithms to be useful in these various applications. Deep learning-based voice conversion algorithms, which have been showing promising results recently, generally consist of three modules: a feature extractor, feature converter, and vocoder. The feature extractor accepts the waveform as the input and extracts speech feature vectors for further processing. These speech feature vectors are later synthesized back into waveforms by the vocoder. The feature converter module performs the actual voice conversion; therefore, many previous studies separately focused on improving this module. These works combined the separately trained vocoder to synthesize the final waveform. Since the feature converter and the vocoder are trained independently, the output of the converter may not be compatible with the input of the vocoder, which causes performance degradation. Furthermore, most voice conversion algorithms utilize mel-spectrogram-based speech feature vectors without modification. These feature vectors have performed well in a variety of speech-processing areas but could be further optimized for voice conversion tasks. To address these problems, we propose a novel wave-to-wave (wav2wav) voice conversion method that integrates the feature extractor, the feature converter, and the vocoder into a single module and trains the system in an end-to-end manner. We evaluated the efficiency of the proposed method using the VCC2018 dataset.

Funder

Basic Science Research Program through the National Research Foundation (NRF) of Korea

NRF

Publisher

MDPI AG

Reference37 articles.

1. Real-time talking avatar on the internet using kinect and voice conversion;Nose;Int. J. Adv. Comput. Sci. Appl.,2015

2. Foreign accent conversion in computer assisted pronunciation training;Felps;Speech Commun.,2009

3. Voice conversion for persons with amyotrophic lateral sclerosis;Zhao;IEEE J. Biomed. Health Inform.,2019

4. Kingma, D.P., and Welling, M. (2014, January 14–16). Auto-encoding variational bayes. Proceedings of the International Conference on Learning Repre-sentations, Banff, AB, Canada.

5. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative adver-sarial nets. Proceedings of the Neural Information Processing Systems, Montreal, QC, Canada.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3