Z
Zhuo Chen
Researcher at Microsoft
Publications - 160
Citations - 6921
Zhuo Chen is an academic researcher from Microsoft. The author has contributed to research in topics: Computer science & Word error rate. The author has an hindex of 29, co-authored 128 publications receiving 4658 citations. Previous affiliations of Zhuo Chen include Mitsubishi Electric & Mitsubishi Electric Research Laboratories.
Papers
More filters
Proceedings ArticleDOI
Deep clustering: Discriminative embeddings for segmentation and separation
TL;DR: In this paper, a deep network is trained to assign contrastive embedding vectors to each time-frequency region of the spectrogram in order to implicitly predict the segmentation labels of the target spectrogram from the input mixtures.
Posted Content
Deep clustering: Discriminative embeddings for segmentation and separation
TL;DR: Preliminary experiments on single-channel mixtures from multiple speakers show that a speaker-independent model trained on two-speaker mixtures can improve signal quality for mixtures of held-out speakers by an average of 6dB, and the same model does surprisingly well with three-speakers mixtures.
Proceedings ArticleDOI
Dual-Path RNN: Efficient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation
Yi Luo,Zhuo Chen,Takuya Yoshioka +2 more
TL;DR: In this paper, a dual-path recurrent neural network (DPRNN) is proposed for modeling extremely long sequences. But the model is not effective for modeling such long sequences due to optimization difficulties, while one-dimensional CNNs cannot perform utterance-level sequence modeling when its receptive field is smaller than the sequence length.
Proceedings ArticleDOI
Deep attractor network for single-microphone speaker separation
Zhuo Chen,Yi Luo,Nima Mesgarani +2 more
TL;DR: A novel deep learning framework for single channel speech separation by creating attractor points in high dimensional embedding space of the acoustic signals which pull together the time-frequency bins corresponding to each source.
Proceedings ArticleDOI
Single-Channel Multi-Speaker Separation using Deep Clustering
Yusuf Ziya Isik,Yusuf Ziya Isik,Jonathan Le Roux,Zhuo Chen,Zhuo Chen,Shinji Watanabe,John R. Hershey +6 more
TL;DR: In this paper, an end-to-end signal approximation objective was proposed to improve the performance of a speaker-independent multi-speaker separation system using deep clustering, which achieved a 10.3 dB improvement in the SDR.