Timezone: »

Fitting New Speakers Based on a Short Untranscribed Sample
Eliya Nachmani · Adam Polyak · Yaniv Taigman · Lior Wolf

Thu Jul 12 09:15 AM -- 12:00 PM (PDT) @ Hall B #64

Learning-based Text To Speech systems have the potential to generalize from one speaker to the next and thus require a relatively short sample of any new voice. However, this promise is currently largely unrealized. We present a method that is designed to capture a new speaker from a short untranscribed audio sample. This is done by employing an additional network that given an audio sample, places the speaker in the embedding space. This network is trained as part of the speech synthesis system using various consistency losses. Our results demonstrate a greatly improved performance on both the dataset speakers, and, more importantly, when fitting new voices, even from very short samples.

Author Information

Eliya Nachmani (Facebook AI Research and Tel Aviv University)
Adam Polyak (Facebook AI Research and Tel Aviv University)
Yaniv Taigman (Facebook)
Lior Wolf (Facebook AI Research and Tel Aviv University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors