 Multi-View Frequency-Attention Alternative to CNN Frontends for
Automatic Speech RecognitionInterspeech (Interspeech), 2023 |
 Time-Frequency Localization Using Deep Convolutional Maxout Neural
Network in Persian Speech RecognitionNeural Processing Letters (NPL), 2021 Arash Dehghani Seyyed Ali Seyyedsalehi |
 Do You Listen with One or Two Microphones? A Unified ASR Model for
Single and Multi-Channel AudioInternational Workshop on Acoustic Signal Enhancement (IWAENC), 2021 |