Yogesh Virkar

automatic dubbing (4) prosodic alignment (2) speech-to-speech translation (2) speech translation (2) audiovisual coherence (2) simultaneous translation (1) end-to-end speech recognition (1) phoneme sequence (1) multilingual speech recognition (1) frame-level alignment (1) neural text-to-speech (1) speaking rate control (1) phrase-level synthesis (1) attention alignment (1) word timing estimation (1) subword alignment (1) hmm-free modeling (1) transformer model (1) speech to speech translation (1) machine translation (1)