|
This article is cited in 1 scientific paper (total in 1 paper)
Topical issue
Cloning and conversion of an arbitrary voice using generative flows
D. S. Obukhov Novosibirsk State Technical University, Novosibirsk, 630073 Russia
Abstract:
To improve the quality of generated speech signals, this paper proposes a method for taking into account time-varying information about the speaker. Using this technique, the system synthesizes more natural speech with a voice similar to the given target voice in both the voice cloning and voice conversion problems.
Keywords:
voice cloning, voice conversion, speech synthesis, streaming generative model, speaker embedding, pitch frequency.
Citation:
D. S. Obukhov, “Cloning and conversion of an arbitrary voice using generative flows”, Avtomat. i Telemekh., 2022, no. 10, 80–93; Autom. Remote Control, 83:10 (2022), 1555–1566
Linking options:
https://www.mathnet.ru/eng/at16053 https://www.mathnet.ru/eng/at/y2022/i10/p80
|
Statistics & downloads: |
Abstract page: | 57 | References: | 20 | First page: | 9 |
|