Sciweavers

910 search results - page 113 / 182
» Standardization of Speech Corpus
Sort
View
ICASSP
2011
IEEE
13 years 14 days ago
Arccosine kernels: Acoustic modeling with infinite neural networks
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
Chih-Chieh Cheng, Brian Kingsbury
ICASSP
2011
IEEE
13 years 14 days ago
A segment-level confidence measure for Spoken Document Retrieval
This paper presents a semantic confidence measure that aims to predict the relevance of automatic transcripts for a task of Spoken Document Retrieval (SDR). The proposed predicti...
Grégory Senay, Georges Linares, Benjamin Le...
ACL
2012
11 years 11 months ago
Using Search-Logs to Improve Query Tagging
Syntactic analysis of search queries is important for a variety of information-retrieval tasks; however, the lack of annotated data makes training query analysis models difficult...
Kuzman Ganchev, Keith Hall, Ryan T. McDonald, Slav...
EMNLP
2010
13 years 6 months ago
NLP on Spoken Documents Without ASR
There is considerable interest in interdisciplinary combinations of automatic speech recognition (ASR), machine learning, natural language processing, text classification and info...
Mark Dredze, Aren Jansen, Glen Coppersmith, Ken Wa...
TSD
2007
Springer
14 years 2 months ago
The Intonational Realization of Requests in Polish Task-Oriented Dialogues
available in the Conference Program). 2007: (with E. Jarmołowicz, Z. Malisz i M. Szczyszek) Gesture, Prosody and Lexicon in ented Dialogues: Progress Report. (Poznań Linguistic M...
Maciej Karpinski