|
CiteSeerX - Document Details (Isaac Councill, Lee Giles): Methods for utterance verification (UV) and their integration into statistical language modeling and spoken language understanding formalisms for a large vocabulary spoken understanding system are presented. ... 30 Stochastic automata for language modeling – Riccardi,
|
citeseer.ist.psu.edu/422293.html
|
|
|
|
Segmenting spoken language utterances into clauses for semantic classification; Gupta, N.K. Bangalore, S. AT&T Labs.-Res., USA; ... Robust spoken language understanding in large-scale conversational dialog applications is usually performed by classification of the user utterances into one or many semantic classes.
|
ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1318495
|
|
|
Prosodic parsing and the notion of utterance in spoken language ... Textual spoken organisation is characterised by utterances, based on a pragmatic nature and corresponding to communicative acts.
|
lablita.dit.unifi.it/coralrom/prosodic_tagging.html
|
|
It will also be shown that spoken language understanding performance can be improved by incorporating acoustic confidence when associating utterances with ...
|
linkinghub.elsevier.com/retrieve/pii/S0167639300000406
|
|
1.8: Spoken Language Understanding ... The speech recognition utterance error rates in the December 1994 benchmarks was about 13% to 25%. The utterance understanding error rates range from 6% to 41%, although about 25% of the utterances are considered unevaluable in the testing paradigm, so these figures do not consider...
|
cslu.cse.ogi.edu/HLTsurvey/ch1node10.html
|
|
P. Heeman and A. McMillin and J. S. Yaruss, "An annotation scheme for complex disfluencies", in Proceedings of the 9th International Conference on Spoken Language Processing, ... Peter A. Heeman and James F. Allen, "Speech Repairs, Intonational Phrases and Discourse Markers: Modeling Speakers' Utterances in Spoken Dialog",
|
cslu.cse.ogi.edu/publications/
|
|
The phonemotactic system recognizes the language spoken 100% of the time when tested on the training data. When tested on the 1994 evaluation test data, the phonotactic system achieves 88 % correct identication of the language spoken for the 50 sec recordings and 76 % correct for the 10 sec utterances.
|
www.asel.udel.edu/icslp/cdrom/vol3/537/a537.pdf
|
|
In contrast, we describe a so-called screening approach for learning robust processing of spontaneously spoken language. A screening approach is a flat analysis which uses shallow sequences of category representations for analyzing an utterance at various syntactic, semantic and dialog levels.
|
www.cs.cmu.edu/afs/cs/project/jair/pub/volume6/wermter9...
www.cs.cmu.edu/afs/cs/project/jair/pub/volume6/wermter97a-html/abstract.html
|
|
Title;Spoken Language Processing. Organizing Situated Utterances of Dialogue and Its Psychological Evaluation. ... TOP > J-EAST > List of Journal Titles (T) > Transactions of Information Processing Society of Japan(1999) > Spoken Language Processing. Organizing Situated Utterances of Dialogue and Its Psychological Evaluation.
|
sciencelinks.jp/j-east/article/199917/000019991799A0378...
sciencelinks.jp/j-east/article/199917/000019991799A0378347.php
|
|
