Affiliation

Contact

  • Email:
  • Voice:
  • Address:
    2805 E. 10th St.
    Smith Research Center Room 152E
    Bloomington, IN 47408


To Prospective Students

  • Send me your CV!

News

(6/8/2016)
I'm joining the faculty of the School of Informatics and Computing at Indiana University Bloomington as an assistant professor starting from the fall semester. Within the school I'll be with the new Intelligent Systems Engineering unit.

(4/28/2016)
I was selected as an Outstanding Teaching Assistant for my TAship in Fall 2015, for the course "Machine Learning for Signal Processing".

(4/21/2016)
I successfully finished my PhD study! Here's my dissertation.

(12/21/2015)
My paper, entitled "Efficient Neighborhood-Based Topic Modeling for Collaborative Audio Enhancement on Massive Crowdsourced Recordings," was accepted in the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2016).

(5/22/2015)
My paper, entitled "Adaptive Denoising Autoencoders: A Fine-tuning Scheme to Learn from Test Mixtures," was nominated for the best student paper on audio signal processing in the International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2015).

(7/11/2015)
My paper, entitled "Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation," was accepted for publication in IEEE/ACM Transactions on Audio, Speech, and Language Processing.

(5/26/2015)
Started my 4th internship at Adobe Research as a Creative Technologies Lab Intern.

(5/22/2015)
My paper, entitled "Adaptive Denoising Autoencoders: A Fine-tuning Scheme to Learn from Test Mixtures," was accepted in the International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2015).

(Show more)

(1/14/2015)
My paper, entitled "Efficient Manifold Preserving Audio Source Separation Using Locality Sensitive Hashing," was accepted in the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2015).

(12/22/2014)
My paper, entitled "Exploiting Structured Human Interactions to Enhance Estimation Accuracy in Cyber-physical Systems," was accepted for publication in the International Conference on Cyber-Physical Systems (ICCPS 2015).

(12/15/2014)
My team was selected as one of the finalists for the Qualcomm Innovation Fellowship 2015.

(12/1/2014)
I passed the preliminary exam (thesis proposal).

(10/26/2014)
My paper, entitled "Collaborative Audio Enhancement: Crowdsourced Audio Recording," was accepted for publication in the NIPS 2014 Workshop on Crowdsourcing and Machine Learning.

(9/15/2014)
My paper, entitled "Efficient Model Selection for Speech Enhancement Using a Deflation Method for Nonnegative Matrix Factorization," was accepted for publication in the IEEE Global Conference on Signal and Information Processing (Global SIP).

(6/27/2014)
My paper, entitled "Mixture of Local Dictionaries for Unsupervised Speech Enhancement," was accepted for publication in the IEEE Signal Processing Letters.

(6/27/2014)
My paper, entitled "Singing-Voice Separation From Monaural Recordings Using Deep Recurrent Neural Networks," was accepted for publication in the International Society for Music Information Retrieval Conference (ISMIR 2014).

(5/19/2014)
Started to work at Adobe Research as a Creative Technologies Lab Intern.

(4/15/2014)
Po-Sen Huang and I won the Starkey Signal Processing Research Student Grant for the paper, "Deep Learning for Monaural Speech Separation (ICASSP 2014)."

(2/3/2014)
Two of my papers, "Phase and Level Difference Fusion for Robust Multichannel Source Separation" and "Deep Learning for Monaural Speech Separation" were accepted for ICASSP 2014.

(7/22/2013)
My paper, entitled "Non-Negative Matrix Factorization for Irregularly-Spaced Transforms," was accepted for publication in the IEEE Int'l Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2013).

(7/9/2013)
My paper, entitled "Single Channel Source Separation Using Smooth Nonnegative Matrix Factorization with Markov Random Fields," was accepted for publication in the IEEE Int'l Workshop on Machine Learning for Signal Processing (MLSP 2013).

(6/23/2013)
I won the Google ICASSP Student Travel Grant for the paper "Collaborative Audio Enhancement Using Probabilistic Latent Component Sharing."

(5/20/2013)
I started to work at Adobe Research as a Creative Technologies Lab Intern.

(4/15/2013)
My paper, entitled "Manifold Preserving Hierarchical Topic Models for Quantization and Approximation," was accepted in the International Conference on Machine Learning (ICML 2013).

(3/17/2013)
My paper, entitled "Collaborative Audio Enhancement Using Probabilistic Latent Component Sharing," was nominated for the Best Student Paper Award at (ICASSP 2013).

(2/28/2013)
My paper, entitled "Collaborative Audio Enhancement Using Probabilistic Latent Component Sharing," was accepted in the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013).

(10/23/2012)
I passed the PhD qualifying exam!

(9/26/2012)
My recent paper, "Stereophonic Spectrogram Segmentation Using Markov Random Fields", was published in the IEEE Workshops on Machine Learning for Signal Processing (MLSP 2012).

(close)

Selected Projects

Bitwise Neural Networks

A super duper compact, yet powerful neural network running on small devices. It uses just a bit of your precious resources.

Collaborative Audio Enhancement

Crowdsource your recording job, and we'll take care of the rest. We can handle up to a thousand crowdsourced recordings.

Manifold Preserving Source Separation

Are you the kind of person who is obsessed with details? You are not alone. Here's our audio enhancement algorithm that preserves the subtlety of human speech, music, and even noise.

Irregular Matrix Factorization

Q: What if my data is not a matrix, but I still want to do NMF on it?
A: Don't worry about it. We've got a weird matrix factorization algorithm that works for the non-matrix data.

Adaptive Model Complexity Estimation from Unknown Signals - A Deflation Method for NMF

You don't want to guess the number of NMF components anymore? Here is a solution, a deflation method for NMF. With this technique, you can estimate the optimal number of components for the unknown noise from the test signal.