Sciweavers

775 search results - page 139 / 155
» Processing Self Corrections in a speech to speech system
Sort
View
FLAIRS
2003
13 years 9 months ago
Orthographic Case Restoration Using Supervised Learning Without Manual Annotation
One challenge in text processing is the treatment of case insensitive documents such as speech recognition results. The traditional approach is to re-train a language model exclud...
Cheng Niu, Wei Li 0003, Jihong Ding, Rohini K. Sri...
CICLING
2010
Springer
14 years 2 months ago
GEMS: Generative Modeling for Evaluation of Summaries
Automated evaluation is crucial in the context of automated text summaries, as is the case with evaluation of any of the language technologies. In this paper we present a Generativ...
Rahul Katragadda
ICASSP
2009
IEEE
14 years 2 months ago
Fast noise PSD estimation with low complexity
Although noise PSD estimation is a crucial part of noise reduction algorithms, most noise PSD estimators have problems in tracking non-stationary noise sources. Recently, a noise ...
Richard C. Hendriks, Richard Heusdens, Jesper Jens...
ICASSP
2008
IEEE
14 years 2 months ago
Environmental sound recognition using MP-based features
Defining suitable features for environmental sounds is an important problem in an automatic acoustic scene recognition system. As with most pattern recognition problems, extracti...
Selina Chu, Shrikanth S. Narayanan, C. C. Jay Kuo
ICASSP
2008
IEEE
14 years 2 months ago
Learning with noisy supervision for Spoken Language Understanding
Data-driven Spoken Language Understanding (SLU) systems need semantically annotated data which are expensive, time consuming and prone to human errors. Active learning has been su...
Christian Raymond, G. Riccardfi