Seamless: Multilingual Expressive and Streaming Speech Translation.
Loïc BarraultYu-An ChungMariano Cora MeglioliDavid DaleNing DongMark DuppenthalerPaul-Ambroise DuquenneBrian EllisHady ElsaharJustin HaaheimJohn HoffmanMin-Jae HwangHirofumi InagumaChristopher KlaiberIlia KulikovPengwei LiDaniel LichtJean MaillardRuslan MavlyutovAlice RakotoarisonKaushik Ram SadagopanAbinesh RamakrishnanTuan TranGuillaume WenzekYilin YangEthan YeIvan EvtimovPierre FernandezCynthia GaoPrangthip HansantiElahe KalbassiAmanda KalletArtyom KozhevnikovGabriel Mejia GonzalezRobin San RomanChristophe TouretCorinne WongCarleigh WoodBokai YuPierre AndrewsCan BaliogluPeng-Jen ChenMarta R. Costa-jussàMaha ElbayadHongyu GongFrancisco GuzmánKevin HeffernanSomya JainJustine KaoAnn LeeXutai MaAlexandre MourachkoBenjamin PeloquinJuan PinoSravya PopuriChristophe RopersSafiyyah SaleemHolger SchwenkAnna SunPaden TomaselloChanghan WangJeff WangSkyler WangMary WilliamsonPublished in: CoRR (2023)
Keyphrases
- language resources
- broadcast news
- cross language information retrieval
- multi lingual
- cross language
- cross language ir
- machine translation
- machine translation system
- cross lingual
- cross lingual information retrieval
- speech recognition
- chinese english
- parallel corpus
- data streams
- comparable corpora
- query translation
- speech signal
- audio visual
- endpoint detection
- real time
- parallel corpora
- streaming data
- recognition engine
- bilingual dictionaries
- text to speech
- digital libraries
- automatic speech recognition
- language independent
- out of vocabulary
- multilingual information retrieval
- video streaming
- context awareness
- spoken language
- speech synthesis
- emotion recognition
- hidden markov models
- word alignment
- streaming media
- speaker identification
- noisy environments
- video streams