Speech Synthesis
Including expressive and controllable text-to-speech synthesis, voice converstion, singing voice synthesis, singing voice conversion ...
Speech Recognition
Including deep learning approaches, keyword spotting, unsupervised pretraining, data augumentation, mispronunciation detection and diagnosis ...
Speaker Recognition
Including speaker verification, speaker representation learning, speaker darization, adversarial attack and defense, anti-spoofing ...
Speech Signal Processing
Including speech enhancement, speech separation, target speaker extraction, singing voice separation ...
Affective Computing
Including speech emotion recognition, emotion recognition in conversations, speech emphasis detection, user intention understanding in speech interactive system ...
Multimodal Speech and Language Processing
Including audio-visual bimodal modeling, talking avatar, audio-visual speech separation, natural language understanding and generation ...