TY - CONF T1 - Perceive and Predict: Self-Supervised Speech Representation Based Loss Functions for Speech Enhancement JO - ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) UR - http://dx.doi.org/10.1109/icassp49357.2023.10095666 PY - 2023/06/04 AU - Close G AU - Ravenscroft W AU - Hain T AU - Goetze S ED - DO - DOI: 10.1109/icassp49357.2023.10095666 PB - IEEE Y2 - 2024/12/26 ER -