3 citations · 3 across the 3 of their papers we have counts for
3 papers
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…
cs.CL2016★ 3 cited
End-to-end attention-based distant speech recognition with Highway LSTM
Hassan Taherian
End-to-end attention-based models have been shown to be competitive alternatives to conventional DNN-HMM models in the Speech Recognition Systems. In this paper, we extend existing…