SANE 2013 - Speech and Audio in the Northeast

October 24, 2013

Low Library Columbia University 8-11-06

The workshop is now over. Slides for the talks are available through the SANE News group.

SANE 2013, a one-day event gathering researchers and students in speech and audio from the Northeast of the American continent, was held on Thursday October 24, 2013 at Columbia University, in New York City.

A follow-up to SANE 2012 held in October at MERL in Cambridge, MA, this year's SANE was held in conjunction with the WASPAA workshop, held October 20-23 in upstate New York. Many WASPAA attendees also attended SANE.

SANE 2013 featured invited speakers from the Northeast, as well as from the international community. It also featured a lively poster session during lunch time, open to both students and researchers.


  • Date: Thursday, October 24, 2013; 9:00am - 5:00pm
  • Venue: Columbia University, New York, NY


8:45-9:15Registration and Breakfast
9:30-10:15Brian Kingsbury (IBM TJ Watson Research Center)
"Keyword Search on Realistically Degraded Speech"
10:15-11:00Yann Lecun (NYU)
"Learning Acoustic (and Visual) Feature Hierarchies"
11:00-11:30Coffee Break
11:30-12:15Mark Plumbley (Queen Mary University of London)
"Making Sense of Sounds"
12:15-1:00Jonathan Le Roux (MERL)
"Extracting speech from clutter using dynamical graphical models"
1:00-3:00Lunch / Poster Session
3:00-3:45Jort Gemmeke (KU Leuven)
"Compositional Models for Self-Taught Vocal Interfaces"
3:45-4:30Hank Liao (Google Research, NYC)
"Google-Scale Speech Recognition"
4:30-4:45Closing remarks

Poster Session

  • "Analysis-by-synthesis feature extraction for automatic speech recognition from partial spectral observations"
    Michael I. Mandel and Arun Narayanan (Ohio State University)
  • "Results on Automated Tuning of a Voice Quality Enhancement System Using Objective Quality Measures"
    Daniele Giacobello, Joshua Atkins, Jason Wung, and Raghavendra Prabhu (Beats by Dr. Dre)
  • "Removing the Effects of Whole Body Vibration Upon Speech"
    Rachel Bittner (NYU)
  • "Ambient Sound-based Proximity Detection with Smartphones"
    Hiroyuki Satoh (The University of Tokyo, Columbia)
  • "An MFCC-GMM Approach For Event Detection And Classification"
    Lode Vuegen (KU Leuven)
  • "Estimating Onset and Offset Asynchronies in Polyphonic Audio-to-Score Alignment"
    Johanna C. Devaney (Ohio State University)
  • "A Generative Product-of-Filters Model of Audio"
    Dawen Liang (Columbia)
  • "Introducing a Simple Fusion Framework for Audio Source Separation"
    Gael RICHARD, Xabier Jaureguiberry, Pierre Leveau, Romain Hennequin and Emmanuel Vincent (Telecom ParisTech, Audionamix, INRIA)
  • "Representation of speech in human auditory cortex"
    Nima Mesgarani (Columbia)
  • "Automatic Chord Recognition with Guitar-Specific Regularization"
    Erik J. Humphrey, Juan Pablo Bello (NYU)
  • "Probabilistic Latent Component Sharing for the Separation of Non-Orthogonally Overlapping Sources"
    Minje Kim, Gautham Mysore, Paris Smaragdis (UIUC, Adobe Research)
  • "Speech Enhancement by Sparse, Low-rank, and Dictionary Spectrogram Decomposition"
    Zhuo Chen (Columbia)


The workshop is now over. If you are interested in attending future SANE events, please sign up to the SANE News mailing list.


The workshop was hosted at the Schapiro Center for Engineering and Physical Science Research, Columbia University, in New York City, NY.

Organizing Committee



MERL Columbia University