C
Chris Bartels
Researcher at University of Maryland, College Park
Publications - 32
Citations - 910
Chris Bartels is an academic researcher from University of Maryland, College Park. The author has contributed to research in topics: Graphical model & Dynamic Bayesian network. The author has an hindex of 13, co-authored 32 publications receiving 846 citations. Previous affiliations of Chris Bartels include University of Washington & Apple Inc..
Papers
More filters
Journal ArticleDOI
Graphical model architectures for speech recognition
Jeff A. Bilmes,Chris Bartels +1 more
TL;DR: This discussion employs dynamic Bayesian networks (DBNs) and a DBN extension using the Graphical Model Toolkit's (GMTK's) basic template, a dynamic graphical model representation that is more suitable for speech and language systems.
Proceedings ArticleDOI
Articulatory Feature-Based Methods for Acoustic and Audio-Visual Speech Recognition: Summary from the 2006 JHU Summer workshop
Karen Livescu,Özgür Çetin,Mark Hasegawa-Johnson,Simon King,Chris Bartels,Nash Borges,Arthur Kantor,Partha Lal,L. Yung,A. Bezman,Stephen Dawson-Haggerty,Bronwyn Woods,Joe Frankel,M. Magami-Doss,Kate Saenko +14 more
TL;DR: This work reports on investigations into the use of articulatory features (AFs) for observation and pronunciation models in speech recognition, and investigates a model having multiple streams of AF states with soft synchrony constraints, for both audio-only and audio-visual recognition.
Proceedings ArticleDOI
Submodular subset selection for large-scale speech training data
TL;DR: This work applies a novel data selection technique based on constrained submodular function maximization to subselecting a large set of acoustic data to train automatic speech recognition (ASR) systems and shows that training data can be reduced significantly, and that the technique outperforms both random selection and a previously proposed selection method utilizing comparable resources.
Proceedings ArticleDOI
DBN based multi-stream models for audio-visual speech recognition
TL;DR: A model based on dynamic Bayesian networks (DBN) to integrate information from multiple audio and visual streams and an absolute improvement of about 4% in word accuracy in the -4 to 10db average case when making use of two audio and one video streams is indicated.
Posted Content
Voices Obscured in Complex Environmental Settings (VOICES) corpus
Colleen Richey,M. A. Barrios,Zeb Armstrong,Chris Bartels,Horacio Franco,Martin Graciarena,Aaron Lawson,Mahesh Kumar Nandwana,Allen R. Stauffer,Julien van Hout,Paul Gamble,J. Hetherly,Cory Stephenson,Karl Ni +13 more
TL;DR: Voices Obscured In Complex Environmental Settings (VOICES) as mentioned in this paper is a large-scale dataset of speech recorded by far-field microphones in noisy room conditions, where audio was recorded in furnished rooms with background noise played in conjunction with foreground speech selected from the LibriSpeech corpus.