Frequency-Directional Attention Model for Multilingual Automatic Speech Recognition

no code implementations • 29 Mar 2022 • Akihiro Dobashi, Chee Siang Leow, Hiromitsu Nishizaki

Furthermore, visualization of the attention weights based on the proposed method suggested that it is possible to transform acoustic features considering the frequency characteristics of each language.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1