103 citations · 423 across the 15 of their papers we have counts for
16 papers
Universal Sound Separation
Ilya Kavalerov, Scott Wisdom, Hakan Erdogan +4
Recent deep learning approaches have achieved impressive performance on speech enhancement and separation tasks. However, these approaches have not been investigated for separating…
Low-Latency Speaker-Independent Continuous Speech Separation
Takuya Yoshioka, Zhuo Chen, Changliang Liu +3
Speaker independent continuous speech separation (SI-CSS) is a task of converting a continuous audio stream, which may contain overlapping voices of unknown speakers, into a fixed…
SDR - half-baked or well done?
Jonathan Le Roux, Scott Wisdom, Hakan Erdogan +1
In speech enhancement and source separation, signal-to-noise ratio is a ubiquitous objective measure of denoising/separation quality. A decade ago, the BSS_eval toolkit was develop…
Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks
Takuya Yoshioka, Hakan Erdogan, Zhuo Chen +2
The goal of this work is to develop a meeting transcription system that can recognize speech even when utterances of different speakers are overlapped. While speech overlaps have b…
Deep Long Short-Term Memory Adaptive Beamforming Networks For Multichannel Robust Speech Recognition
Zhong Meng, Shinji Watanabe, John R. Hershey +1
Far-field speech recognition in noisy and reverberant conditions remains a challenging problem despite recent deep learning breakthroughs. This problem is commonly addressed by acq…
PLDA-Based Diarization of Telephone Conversations
Ahmet E. Bulut, Hakan Demir, Yusuf Ziya Isik +1
This paper investigates the application of the probabilistic linear discriminant analysis (PLDA) to speaker diarization of telephone conversations. We introduce using a variational…