Convolutive Transfer Function Invariant SDR Training Criteria for Multi-Channel Reverberant Speech Separation

Christoph Böddeker, Wangyou Zhang, Tomohiro Nakatani, Keisuke Kinoshita, Tsubasa Ochiai, Marc Delcroix, Naoyuki Kamo, Yanmin Qian, Reinhold Haeb-Umbach. Convolutive Transfer Function Invariant SDR Training Criteria for Multi-Channel Reverberant Speech Separation. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021. pages 8428-8432, IEEE, 2021. [doi]

Authors

Christoph Böddeker

This author has not been identified. Look up 'Christoph Böddeker' in Google

Wangyou Zhang

This author has not been identified. Look up 'Wangyou Zhang' in Google

Tomohiro Nakatani

This author has not been identified. Look up 'Tomohiro Nakatani' in Google

Keisuke Kinoshita

This author has not been identified. Look up 'Keisuke Kinoshita' in Google

Tsubasa Ochiai

This author has not been identified. Look up 'Tsubasa Ochiai' in Google

Marc Delcroix

This author has not been identified. Look up 'Marc Delcroix' in Google

Naoyuki Kamo

This author has not been identified. Look up 'Naoyuki Kamo' in Google

Yanmin Qian

This author has not been identified. Look up 'Yanmin Qian' in Google

Reinhold Haeb-Umbach

This author has not been identified. Look up 'Reinhold Haeb-Umbach' in Google