Unbabel Talk: Difference between revisions
From HLT@INESC-ID
m (Add link section) |
m (Correct some typos) |
||
| (One intermediate revision by the same user not shown) | |||
| Line 2: | Line 2: | ||
Unbabel Talk is a speech-to-speech translation application that | Unbabel Talk is a speech-to-speech translation application that | ||
provides human certified translations for voice instant | provides human certified translations for voice instant messaging (IM) | ||
in multilingual scenarios. By combining Unbabel’s translation pipeline | |||
with state-of-the-art automatic speech recognition (ASR) and | |||
recognition (ASR) and text-to-speech (TTS) models, Unbabel | text-to-speech (TTS) models, Unbabel Talk can be used to send | ||
Talk can be used to send a voice message in a language of | a voice message in a language of | ||
choice through popular messaging platforms. The app further | choice through popular messaging platforms. The app further | ||
ensures that translations have high quality, either by | ensures that translations have high quality, either by certifying them | ||
through Unbabel’s own quality estimation (QE) tool | |||
and/or through Unbabel’s community of translators. There are | and/or through Unbabel’s community of translators. There are | ||
two versions of the app. On version 1, the app synthesizes audio | two versions of the app. On version 1, the app synthesizes audio | ||
that can be delivered with male or female standard voices. | that can be delivered with male or female standard voices. Version 2 | ||
has features that are currently being developed, such as | |||
voice morphing and transcription correction through Unbabel’s | voice morphing and transcription correction through Unbabel’s | ||
community. | community. | ||
| Line 26: | Line 26: | ||
[[Helena_Moniz|Helena Moniz]] | [[Helena_Moniz|Helena Moniz]] | ||
[[category:Demos]] | |||
Latest revision as of 15:59, 28 November 2020
Abstract
Unbabel Talk is a speech-to-speech translation application that provides human certified translations for voice instant messaging (IM) in multilingual scenarios. By combining Unbabel’s translation pipeline with state-of-the-art automatic speech recognition (ASR) and text-to-speech (TTS) models, Unbabel Talk can be used to send a voice message in a language of choice through popular messaging platforms. The app further ensures that translations have high quality, either by certifying them through Unbabel’s own quality estimation (QE) tool and/or through Unbabel’s community of translators. There are two versions of the app. On version 1, the app synthesizes audio that can be delivered with male or female standard voices. Version 2 has features that are currently being developed, such as voice morphing and transcription correction through Unbabel’s community.