Flexible Evidence Model to Reduce Uncertainty Mismatch Between Speech Enhancement and ASR Based on Encoder-Decoder Architecture

Ryu Takeda, Yui Sudo, Kazunori Komatani. Flexible Evidence Model to Reduce Uncertainty Mismatch Between Speech Enhancement and ASR Based on Encoder-Decoder Architecture. In Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023, Taipei, Taiwan, October 31 - Nov. 3, 2023. pages 1830-1837, IEEE, 2023. [doi]

Authors

Ryu Takeda

This author has not been identified. Look up 'Ryu Takeda' in Google

Yui Sudo

This author has not been identified. Look up 'Yui Sudo' in Google

Kazunori Komatani

This author has not been identified. Look up 'Kazunori Komatani' in Google