Continuous speech recognition results of the BYBLOS system on the DARPA 1000-word resource management database

Kubala, Francis; Chow, Yen‐Lu; Derr, A.; Feng, Ming-Whei; Kimball, Owen; Makhoul, John; Price, Patti; Rohlíček, Ján; Roucos, S.; Schwartz, Richard; Vandegrift, J.

doi:10.1109/icassp.1988.196573

Cited by 16 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These conditions are not those that would be used in a real application, but they are simply defined, allow recognition systems to be evaluated over more than one condition of grammatical constraint, and they have been accepted as standards of comparisons. The degree of constraint provided by the grammar is measured by test set perplexity [7], or, the geometric mean of the number of words allowed by the grammar at each point in the test set, given the previous words. In the case of no grammatical constraint, any word can follow any other word and the perplexity is equal to the vocabulary size, in this case 1000.…”

Section: Databasementioning

confidence: 99%

See 1 more Smart Citation

SRI's DECIPHER system

Murveit¹,

Cohen²,

Price³

et al. 1989

Proceedings of the Workshop on Speech and Natural Language - HLT '89

View full text Add to dashboard Cite

SRI has developed a speaker-independent continuous speech, large vocabulary speech recognition system, DECIPHER, that provides state-of-theart performance on the DARPA standard speakerindependent resource management training and testing materials. SRI's approach is to integrate speech and linguistic knowledge into the HMM framework. This paper describes performance improvements arising from detailed phonological modeling and from the incorporation of crossword coarticulatory constraints.

show abstract

Section: Databasementioning

confidence: 99%

“…The use of phonetic units allows for larger vocabularies by sharing training across subword units that repeat more frequently than words do. Phonetic-based units are now common to many HMMbased recognizers (e.g., [7,8,10]).…”

Section: Introductionmentioning

confidence: 99%

SRI's DECIPHER system

Murveit¹,

Cohen²,

Price³

et al. 1989

Proceedings of the Workshop on Speech and Natural Language - HLT '89

View full text Add to dashboard Cite

show abstract

“…The vocabulary of the Resource Management database is 991 words. There is also an "official" word-pair recognition grammar [11]. This grammar is just a list of allowable word pairs without probabilities for the purpose of reducing the recognition perplexity to about 60.…”

Section: Introductionmentioning

confidence: 99%

The Lincoln Continuous Speech Recognition system: recent developments and results

Paul¹

1989

Proceedings of the Workshop on Speech and Natural Language - HLT '89

View full text Add to dashboard Cite

The Lincoln stress-resistant HMM CSR has been extended to large vocabulary continuous speech for both speaker-dependent (SD) and speaker-independent (SI) tasks. Performance on the DARPA Resource Management task (991 word vocabulary, perplexity 60 word-pair grammar) [1] is 3.4% word error rate for SD training of word-context-dependent triphone models and 12.6% word error rate for SI training of (word-context-free) tied mixture triphone models.

show abstract

“…It is important to observe that the language model provides top-down information to reduce the search space during processing. Kubala et al (1988) have shown that the perplexity (roughly the number of choices) of the language model correlates with recognition performance. Because of the tendency for Finite State language models to drastically increase in perplexity as coverage increases, it is unlikely that these systems will extend to spoken language systems.…”

Section: Introductionmentioning

confidence: 99%

Chart parsing of stochastic spoken language models

Hemphill¹

1989

Proceedings of the Workshop on Speech and Natural Language - HLT '89

View full text Add to dashboard Cite

Performance in speech recognition systems has progressed to the point where it is now realistic to begin integrating speech with natural language systems to produce spoken language systems. Two factors have contributed to the advances in speech: statistical modeling of the input signal and language constraints. To produce spoken language systems, then, the grammar formalisms used in natural language systems must incorporate statistical information and efficient parsers for these stochastic language models must be developed. In this paper we outline how chart parsing techniques provide advantages in both computation and accuracy for spoken language systems. We describe a system that models all levels of the spoken language system using stochastic language models and present experimental results.

show abstract

Continuous speech recognition results of the BYBLOS system on the DARPA 1000-word resource management database

Cited by 16 publications

References 8 publications

SRI's DECIPHER system

SRI's DECIPHER system

The Lincoln Continuous Speech Recognition system: recent developments and results

Chart parsing of stochastic spoken language models

Contact Info

Product

Resources

About