ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing
DOI: 10.1109/icassp.1988.196669
|View full text |Cite
|
Sign up to set email alerts
|

The DARPA 1000-word resource management database for continuous speech recognition

Abstract: P a t t i Price W i l l i a m M. Fisher J a r e d B e r n s t e i n

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
92
0
1

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 239 publications
(93 citation statements)
references
References 3 publications
0
92
0
1
Order By: Relevance
“…The second dataset, RM-3000 [32], consists of 3000 sentences spoken by a single native English speaking male speaker. The sentences were randomly selected from the 8000 sentences in the Resource Management (RM) Corpus [33]. The vocabulary size of 1000 words and no strict grammar give a more realistic environment, and more challenging task when compared to GRID.…”
Section: Resultsmentioning
confidence: 99%
“…The second dataset, RM-3000 [32], consists of 3000 sentences spoken by a single native English speaking male speaker. The sentences were randomly selected from the 8000 sentences in the Resource Management (RM) Corpus [33]. The vocabulary size of 1000 words and no strict grammar give a more realistic environment, and more challenging task when compared to GRID.…”
Section: Resultsmentioning
confidence: 99%
“…The initial work developing and implementing the above described stack decoder was performed using the Resource Management (RM) database [18]. The WSJ-pilot database training and development-test data has only been fully available for about 5 weeks (as of this writing) and therefore the number of experiments that have been performed on it is limited.…”
Section: Recognition Resultsmentioning
confidence: 99%
“…Previous work focused on a 1K word task, Resource Management (RM) [18], which could be handled adequately with the TS decoder. (The same decoder was also used on the ATIS task [13].)…”
Section: Introductionmentioning
confidence: 99%
“…It has enabled us to use cross-word-bonndary triphone models and trigram language models with ease. During most of the development of the system we used the 1000-Word RM cospus [8] for testing. More recently, the system has been used for recognizing spontaneous speech from the ATIS corpus, which contains many spontaneous speech effects, such as partial words, nonspeech sounds, extraneous.noises, false starts, etc.…”
Section: Byblosmentioning
confidence: 99%