output
20152025
most citedThe Sound Demixing Challenge 2023 $\unicode{x2013}$ Music Demixing Track

26 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing 2021Show all

1 paper · 1 filter

eess.AS2021

Gaussian Kernelized Self-Attention for Long Sequence Data and Its Application to CTC-based Speech Recognition

Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe

Self-attention (SA) based models have recently achieved significant performance improvements in hybrid and end-to-end automatic speech recognition (ASR) systems owing to their flex…