Embedded thumbnail for On The Forgetting Of College Academics And The Role Of Learning Engineering In Building Expertise
Recorded:
Feb 10, 2017
Uploaded:
February 10, 2017
Part of
CBMM Special Seminars
Speaker(s):
Brian Subirana, Bror Saxberg
Dr. Brian Subirana & Dr. Bror Saxberg In this talk, Brian Subirana will first review research conducted over the last 120 years since Ebbinghaus's seminal work in 1885 on the forgetting curve. This review (joint work in progress with Aikaterini...
Embedded thumbnail for Multilingual representations for low-resource speech processing
Recorded:
Feb 3, 2017
Uploaded:
February 10, 2017
Part of
Speech Representation, Perception and Recognition
Speaker(s):
Brian Kingsbury
Brian Kingsbury, IBM Abstract: A key to achieving good automatic speech recognition performance has been the availability of vast amounts of labeled and unlabeled speech and text data that can be used to train speech models; however, there are...
Embedded thumbnail for Unsupervised Learning of Spoken Language with Visual Context
Recorded:
Feb 3, 2017
Uploaded:
February 10, 2017
Part of
Speech Representation, Perception and Recognition
Speaker(s):
Jim Glass
Jim Glass, MIT Abstract: Despite continuous advances over many decades, automatic speech recognition remains fundamentally a supervised learning scenario that requires large quantities of annotated training data to achieve good performance. This...
Embedded thumbnail for Predicting and perceiving degraded speech
Recorded:
Feb 3, 2017
Uploaded:
February 10, 2017
Part of
Speech Representation, Perception and Recognition
Speaker(s):
Matt Davis
Matt Davis, MRC Cognition and Brain Sciences Unit
Embedded thumbnail for Deep Generative Models for Speech and Images
Recorded:
Feb 3, 2017
Uploaded:
February 10, 2017
Part of
Speech Representation, Perception and Recognition
Speaker(s):
Yoshua Bengio
Yoshua Bengio, U. Montreal
Embedded thumbnail for Generative Model-Based Text-to-Speech Synthesis
Recorded:
Feb 3, 2017
Uploaded:
February 10, 2017
Part of
Speech Representation, Perception and Recognition
Speaker(s):
Heiga Zen
Heiga Zen, Google Abstract: Recent progress in generative modeling has improved the naturalness of synthesized speech significantly.  In this talk I will summarize these generative model-based approaches for speech synthesis and describe possible...
Embedded thumbnail for Learning with Symmetry and Invariance for Speech Perception
Recorded:
Feb 2, 2017
Uploaded:
February 10, 2017
Part of
Speech Representation, Perception and Recognition
CBMM Speaker(s):
Georgios Evangelopoulos
Georgios Evangelopoulos, (CBMM, MIT)
Embedded thumbnail for A data explanatory account of speech perception (and its limits)
Recorded:
Feb 2, 2017
Uploaded:
February 8, 2017
Part of
Speech Representation, Perception and Recognition
Speaker(s):
Bob McMurray
Bob McMurray, U. Iowa Abstract: One of the most challenging aspects of speech perception is the rampant variability in the signal. One consequence of this variability is that purely bottom up approaches to categorizing phonemes have not consistently...
Embedded thumbnail for Acoustic word embeddings
Recorded:
Feb 2, 2017
Uploaded:
February 8, 2017
Part of
Speech Representation, Perception and Recognition
Speaker(s):
Karen Livescu
Karen Livescu, TTI Abstract: For a number of speech tasks, it can be useful to represent speech segments of arbitrary length by fixed-dimensional vectors, or embeddings.  In particular, vectors representing word segments -- acoustic word embeddings...
Embedded thumbnail for Entrainment, segmentation, and decoding: three necessary computations for speech comprehension
Recorded:
Feb 2, 2017
Uploaded:
February 8, 2017
Part of
Speech Representation, Perception and Recognition
Speaker(s):
David Poeppel
David Poeppel, Max-Planck-Institute and NYU Abstract: Neurophysiological experiments demonstrate that auditory cortical activity entrains to continuous speech. This entrainment, building on neural oscillations, underlies segmentation, and the...

Pages