IEEE International Conference on Acoustics Speech and Signal Processing 2002
DOI: 10.1109/icassp.2002.5743648
|View full text |Cite
|
Sign up to set email alerts
|

Adaptive language models for spoken dialogue systems

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2006
2006
2019
2019

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 10 publications
(3 citation statements)
references
References 13 publications
0
3
0
Order By: Relevance
“…In practice, we rather envision the selection of differerent subcomponents of the same LM as being dependent on the recognition of certain words. Such adaptive LMs have been used for quite some time by the speech and language technology community (Jelinek, Merialdo, Roukos, & Strauss, 1991;Solsona, Fosler-Lussier, Kuo, Potamianos, & Zitouni, 2002).…”
Section: Application Perspective: Language Technology Settingmentioning
confidence: 99%
“…In practice, we rather envision the selection of differerent subcomponents of the same LM as being dependent on the recognition of certain words. Such adaptive LMs have been used for quite some time by the speech and language technology community (Jelinek, Merialdo, Roukos, & Strauss, 1991;Solsona, Fosler-Lussier, Kuo, Potamianos, & Zitouni, 2002).…”
Section: Application Perspective: Language Technology Settingmentioning
confidence: 99%
“…It plays an important role in many applications, e.g. automatic speech recognition (ASR) [2], [3], spoken dialog systems [4], and statistical machine translation [5] since it provides some apriori probabilities of word sequences.…”
Section: Introductionmentioning
confidence: 99%
“…In Spoken Dialogue Systems, in which each module performs a different task (speech recognition, language understanding, dialogue management, and so on), the number of potential information sources increases. We could take into account lexical and acoustic information (managed by the speech recognizer), but we could also use semantic information (the content of the recognized utterance, such as in Visweswariah and Printz (2001); Solsona et al (2002); Gruenstein et al (2005)), or discourse or pragmatic information (related to the intentions of the user). These dialogue-based approaches are usually defined as context-dependent adaptation (Fügen et al, 2004;López-Cózar and Griol, 2010), or state-dependent adaptation (Popovici and Baggia, 1997;Riccardi et al, 1998;Riccardi and Gorin, 2000).…”
Section: Lm Adaptation Methodologiesmentioning
confidence: 99%