Po-Sen Huang

发表

How to put it into words - using random forests to extract symbol level descriptions from audio content for concept detection

Mark Hasegawa-Johnson, Gerald Friedland, Ajay Divakaran, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Active Planning, Sensing, and Recognition Using a Resource-Constrained Discriminant POMDP

Lydia E. Kavraki, Thomas S. Huang, Mark Hasegawa-Johnson, 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

Pooling Robust Shift-Invariant Sparse Representations of Acoustic Signals

Thomas S. Huang, Mark Hasegawa-Johnson, Jianchao Yang, 2012, INTERSPEECH.

Singing-Voice Separation from Monaural Recordings using Deep Recurrent Neural Networks

Paris Smaragdis, Mark Hasegawa-Johnson, Minje Kim, 2014, ISMIR.

Opportunistic sensing: Unattended acoustic sensor selection using crowdsourcing models

Thomas S. Huang, Mark Hasegawa-Johnson, Wotao Yin, 2012, 2012 IEEE International Workshop on Machine Learning for Signal Processing.

Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation

Paris Smaragdis, Mark Hasegawa-Johnson, Minje Kim, 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

On the Applicability of Speaker Diarization to Audio Indexing of Non-Speech and Mixed Non-Speech/Speech Video Soundtracks

Mark Hasegawa-Johnson, Gerald Friedland, Ajay Divakaran, 2012, Int. J. Multim. Data Eng. Manag..

Cross-Dialectal Data Transferring for Gaussian Mixture Model Training in Arabic Speech Recognition

Mark Hasegawa-Johnson, Po-Sen Huang, 2012 .

Multi-sensory features for personnel detection at border crossings

Mark Hasegawa-Johnson, Thyagaraju Damarla, Po-Sen Huang, 2011, 14th International Conference on Information Fusion.

Deep learning for monaural speech separation

Paris Smaragdis, Mark Hasegawa-Johnson, Minje Kim, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Singing-voice separation from monaural recordings using robust principal component analysis

Paris Smaragdis, Mark Hasegawa-Johnson, Scott Deeann Chen, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving acoustic event detection using generalizable visual features and multi-modality modeling

Mark Hasegawa-Johnson, Xiaodan Zhuang, Po-Sen Huang, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A block-based 2D-to-3D conversion system with bilateral filter

Liang-Gee Chen, Chung-Te Li, Yi-Min Tsai, 2009, 2009 Digest of Technical Papers International Conference on Consumer Electronics.

Self-supervised Adversarial Robustness for the Low-label, High-data Regime

Pushmeet Kohli, Sven Gowal, Aäron van den Oord, 2021, ICLR.