Sciweavers

76 search results - page 10 / 16
» Using spatial cues for meeting speech segmentation
Sort
View
ICCV
2007
IEEE
14 years 9 months ago
Recovering Occlusion Boundaries from a Single Image
Occlusion reasoning, necessary for tasks such as navigation and object search, is an important aspect of everyday life and a fundamental problem in computer vision. We believe tha...
Derek Hoiem, Andrew N. Stein, Alexei A. Efros, Mar...
ICASSP
2011
IEEE
12 years 11 months ago
Discriminatively estimated discrete, parametric and smoothed-discrete duration models for speech recognition
Duration of phonemic segments provide important cues for distinguishing words in languages such as Arabic. Recently, we proposed a discriminatively estimated joint acoustic, durat...
Maider Lehr, Izhak Shafran
CLEAR
2007
Springer
166views Biometrics» more  CLEAR 2007»
14 years 1 months ago
The IBM Rich Transcription 2007 Speech-to-Text Systems for Lecture Meetings
The paper describes the IBM systems submitted to the NIST Rich Transcription 2007 (RT07) evaluation campaign for the speechto-text (STT) and speaker-attributed speech-to-text (SAST...
Jing Huang, Etienne Marcheret, Karthik Visweswaria...
ECCV
2008
Springer
14 years 9 months ago
Segmentation and Recognition Using Structure from Motion Point Clouds
We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3...
Gabriel J. Brostow, Jamie Shotton, Julien Fauqueur...
ISWC
1998
IEEE
13 years 12 months ago
Speaking and Listening on the Run: Design for Wearable Audio Computing
The use of speech and auditory interaction on wearable computers can provide an awareness of events and personal messages, without requiring one's full attention or disruptin...
Nitin "Nick" Sawhney, Chris Schmandt