arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.04540cs.SDstat.ML
收藏

跨模态语音转换

Crossmodal Voice Conversion

NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation(日本电报电话公司NTT通信科学实验室)

Hirokazu Kameoka, Kou Tanaka, Aaron Valero Puche, Yasunori Ohishi, Takuhiro Kaneko

摘要:

人类能够从一个人的外表想象出他的声音,从他/她的声音想象出他/她的外表。在本文中,我们第一次尝试开发一种方法,可以将语音转换成与输入人脸图像相匹配的语音,并通过利用人脸和语音之间的相关性来生成与输入语音相匹配的人脸图像。我们提出了一个模型,包括一个语音转换器,人脸编码器/解码器和语音编码器。我们使用由人脸编码器编码的输入人脸图像的潜码作为语音转换器的辅助输入,并对语音转换器进行训练,使得语音编码器可以从生成的语音中恢复原始潜码。我们还训练人脸解码器和人脸编码器,以确保潜在代码包含足够的信息来重建输入的人脸图像。我们通过实验证实,以这种方式训练的语音转换器能够将输入语音转换为与输入面部图像相匹配的语音,并且语音编码器和面部解码器可以用于生成与输入语音的语音相匹配的面部图像。

英文摘要:

Humans are able to imagine a person's voice from the person's appearance and imagine the person's appearance from his/her voice. In this paper, we make the first attempt to develop a method that can convert speech into a voice that matches an input face image and generate a face image that matches the voice of the input speech by leveraging the correlation between faces and voices. We propose a model, consisting of a speech converter, a face encoder/decoder and a voice encoder. We use the latent code of an input face image encoded by the face encoder as the auxiliary input into the speech converter and train the speech converter so that the original latent code can be recovered from the generated speech by the voice encoder. We also train the face decoder along with the face encoder to ensure that the latent code will contain sufficient information to reconstruct the input face image. We confirmed experimentally that a speech converter trained in this way was able to convert input speech into a voice that matched an input face image and that the voice encoder and face decoder can be used to generate a face image that matches the voice of the input speech.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑