Raising Robovoices: New systems can model and synthesize voices, and even translate them into other languages.
In: Communications of the ACM, Jg. 65 (2022-05-01), Heft 5, S. 30-31
serialPeriodical
Zugriff:
The article discusses technological advances in the synthesis and modeling of the human voice via machine learning, including the development of what is referred to as automatic speech-to-speech translation. The article also states that the technology may allow for the generation of speech in several different languages.
Titel: |
Raising Robovoices: New systems can model and synthesize voices, and even translate them into other languages.
|
---|---|
Autor/in / Beteiligte Person: | Mone, Gregory |
Zeitschrift: | Communications of the ACM, Jg. 65 (2022-05-01), Heft 5, S. 30-31 |
Veröffentlichung: | 2022 |
Medientyp: | serialPeriodical |
ISSN: | 0001-0782 (print) |
DOI: | 10.1145/3524019 |
Schlagwort: |
|
Sonstiges: |
|