
Modelos estadísticos para transcripción automática, traducción automática y síntesis del habla
Demonstrator
vrain
Demonstrator
vrainStatistical models of speech recognition (ET;FR;IT;NL;PT) and machine translation (ET,FR,IT,NL,PT>EN; EN>IT) developed by the MLLP research group (VRAIN, Universitat Politècnica de València). Neural models of speech recognition (CA,SL,EN,ES,DE,PT,IT,NL,FR) developed by the MLLP research group. Neural machine translation moel (EN>{FR,SL,ES,DE,IT}; {FR,SL,ES,DE,IT,NL}>EN; FR<>DE; ES<>PT) developed by the MLLP research group. Neural models of speech synthesis (EN,ES,CA) developed by the MLLP research group.
Automatic transcription of video/audio in several languages, in real time or delayed. Automatic translation of subtitles or text in several languages, in real time or delayed. Speech synthesis in several languages, in real time or delayed. Comprehensive voice-to-voice dubbing, in real time or recorded.
Automatic Speech Recognition (ASR) Machine Translation (MT) Speech synthesis.