Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations



Hiroshi Sato , Tsubasa Ochiai , Marc Delcroix , Keisuke Kinoshita , Takafumi Moriya , Naoki Makishima , Mana Ihori , Tomohiro Tanaka , Ryo Masumura

* 5 pages, 2 figures, 3 tables Submitted to Interspeech 2022 

   Access Paper or Ask Questions

Mask-based Neural Beamforming for Moving Speakers with Self-Attention-based Tracking



Tsubasa Ochiai , Marc Delcroix , Tomohiro Nakatani , Shoko Araki

* 11 pages, 7 figures, Submitted to IEEE/ACM Trans. Audio, Speech, and Language Processing 

   Access Paper or Ask Questions

Listen only to me! How well can target speech extraction handle false alarms?



Marc Delcroix , Keisuke Kinoshita , Tsubasa Ochiai , Katerina Zmolikova , Hiroshi Sato , Tomohiro Nakatani

* Submitted to Inerspeech 2022 

   Access Paper or Ask Questions

SoundBeam: Target sound extraction conditioned on sound-class labels and enrollment clues for increased performance and continuous learning



Marc Delcroix , Jorge Bennasar Vázquez , Tsubasa Ochiai , Keisuke Kinoshita , Yasunori Ohishi , Shoko Araki

* Submitted to IEEE/ACM Trans. Audio, Speech, and Language Processing 

   Access Paper or Ask Questions

Tight integration of neural- and clustering-based diarization through deep unfolding of infinite Gaussian mixture model



Keisuke Kinoshita , Marc Delcroix , Tomoharu Iwata

* Accepted to IEEE ICASSP-2022, 5 pages, 2 figures 

   Access Paper or Ask Questions

How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR



Kazuma Iwamoto , Tsubasa Ochiai , Marc Delcroix , Rintaro Ikeshita , Hiroshi Sato , Shoko Araki , Shigeru Katagiri

* 5 pages, 5 figures 

   Access Paper or Ask Questions

Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition



Hiroshi Sato , Tsubasa Ochiai , Marc Delcroix , Keisuke Kinoshita , Naoyuki Kamo , Takafumi Moriya

* 5 pages, 2 figures 

   Access Paper or Ask Questions

Attention-based Multi-hypothesis Fusion for Speech Summarization



Takatomo Kano , Atsunori Ogawa , Marc Delcroix , Shinji Watanabe


   Access Paper or Ask Questions

Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model



Martin Kocour , Kateřina Žmolíková , Lucas Ondel , Ján Švec , Marc Delcroix , Tsubasa Ochiai , Lukáš Burget , Jan Černocký

* submitted to ICASSP 2022 

   Access Paper or Ask Questions

SA-SDR: A novel loss function for separation of meeting style data



Thilo von Neumann , Keisuke Kinoshita , Christoph Boeddeker , Marc Delcroix , Reinhold Haeb-Umbach

* submitted to ICASSP 2022 

   Access Paper or Ask Questions

1
2
3
4
>>