activity
20162025
most citedEnd-to-end attention-based distant speech recognition with Highway LSTM

3 citations · 4 across the 7 of their papers we have counts for

collaborators
Showing 2023Show all

2 papers · 1 filter

eess.AS2023

Multi-channel Conversational Speaker Separation via Neural Diarization

Hassan Taherian, DeLiang Wang

When dealing with overlapped speech, the performance of automatic speech recognition (ASR) systems substantially degrades as they are designed for single-talker speech. To enhance…

eess.AS2023

Multi-resolution location-based training for multi-channel continuous speech separation

Hassan Taherian, DeLiang Wang

The performance of automatic speech recognition (ASR) systems severely degrades when multi-talker speech overlap occurs. In meeting environments, speech separation is typically per…