Embedded thumbnail for Multilingual representations for low-resource speech processing
Uploaded:
February 10, 2017
Part of
Speech Representation, Perception and Recognition
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
Uploaded:
February 10, 2017
Part of
Speech Representation, Perception and Recognition
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 Deep Generative Models for Speech and Images
Uploaded:
February 10, 2017
Part of
Speech Representation, Perception and Recognition
Yoshua Bengio, U. Montreal
Embedded thumbnail for Generative Model-Based Text-to-Speech Synthesis
Uploaded:
February 10, 2017
Part of
Speech Representation, Perception and Recognition
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
Uploaded:
February 10, 2017
Part of
Speech Representation, Perception and Recognition
Georgios Evangelopoulos, (CBMM, MIT)
Embedded thumbnail for A data explanatory account of speech perception (and its limits)
Uploaded:
February 8, 2017
Part of
Speech Representation, Perception and Recognition
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
Uploaded:
February 8, 2017
Part of
Speech Representation, Perception and Recognition
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
Uploaded:
February 8, 2017
Part of
Speech Representation, Perception and Recognition
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...
Embedded thumbnail for The role(s) of hemispheric asymmetries and streams of processing in speech perception.
Uploaded:
February 8, 2017
Part of
Speech Representation, Perception and Recognition
Sophie Scott, UCL Abstract: I will talk about the potential for different perceptual representations of the speech signal and their relationship to anatomical and task based factors.
Embedded thumbnail for The promise of ASR: where we stand and what is still missing
Uploaded:
February 7, 2017
Part of
Speech Representation, Perception and Recognition
Abdelrahman Mohamed, Microsoft Research Abstract: In the past decade, the ASR technology made a huge leap forward in terms of word recognition accuracy, leading to the recent announcement of Microsoft of achieving human parity in conversational...

Pages