Author of the publication

Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition.

, , , , , and . Interspeech, page 1149-1153. ISCA, (2021)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

 

Other publications of authors with the same name

Does speech enhancement work with end-to-end ASR objectives?: Experimental analysis of multichannel end-to-end ASR., , and . MLSP, page 1-6. IEEE, (2017)Simpleflat: A Simple Whole-Network Pre-Training Approach for RNN Transducer-Based End-to-End Speech Recognition., , , , , , , , and . ICASSP, page 5664-5668. IEEE, (2021)A Unified Framework for Neural Speech Separation and Extraction., , , , and . ICASSP, page 6975-6979. IEEE, (2019)Beam-TasNet: Time-domain Audio Separation Network Meets Frequency-domain Beamformer., , , , , and . ICASSP, page 6384-6388. IEEE, (2020)DNN-supported Mask-based Convolutional Beamforming for Simultaneous Denoising, Dereverberation, and Source Separation., , , , , , and . ICASSP, page 6399-6403. IEEE, (2020)Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance., , , , , , and . CoRR, (2024)End-to-End SpeakerBeam for Single Channel Target Speech Recognition., , , , , , and . INTERSPEECH, page 451-455. ISCA, (2019)Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data., , , , , , , , , and . INTERSPEECH, page 899-903. ISCA, (2023)Speaker Activity Driven Neural Speech Extraction., , , , and . ICASSP, page 6099-6103. IEEE, (2021)Automatic node selection for Deep Neural Networks using Group Lasso regularization., , , and . ICASSP, page 5485-5489. IEEE, (2017)