Spontaneous speech effects in large vocabulary speech recognition applications

Butzberger, John; Murveit, Hy; Shriberg, Elizabeth; Price, Patti

doi:10.3115/1075527.1075607

Cited by 37 publications

(21 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SRI SLS employs the DECIPHER tm speech recognition system [4] serially connected to SRI's Template Matcher system [7,1]. The pnming threshold of the recognizer was tuned so that system response time was about 2.5 times utterance duration.…”

Section: Methodsmentioning

confidence: 99%

Subject-based evaluation measures for interactive spoken language systems

Price

Hirschman²,

Shriberg

et al. 1992

Proceedings of the Workshop on Speech and Natural Language - HLT '91

Self Cite

View full text Add to dashboard Cite

The DARPA Spoken Language effort has profited greatly from its emphasis on tasks and common evaluation metrics. Common, standardized evaluation procedures have helped the community to focus research effort, to measure progress, and to encourage communication among participating sites. The task and the evaluation metrics, however, must be consistent with the goals of the Spoken Language program, namely interactive problem solving. Our evaluation methods have evolved with the technology, moving from evaluation of read speech from a fixed corpus through evaluation of isolated canned sentences to evaluation of spontaneous speech in context in a canned corpus. A key component missed in current evaluations is the role of subject interaction with the system. Because of the great variability across subjects, however, it is necessary to use either a large number of subjects or a within-subject design. This paper proposes a within-subject design comparing the results of a software-sharing exercise carried out jointly by M1T and SRI.

show abstract

Section: Methodsmentioning

confidence: 99%

Subject-based evaluation measures for interactive spoken language systems

Price

Hirschman²,

Shriberg

et al. 1992

Proceedings of the Workshop on Speech and Natural Language - HLT '91

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several of DECIPHERr~'s attributes are discussed in the references (Butzberger et al, [1]; Murveit et al, [2]). Until recently, DECIPHERm's application has been limited to DARPA's resource management task (Pallet, [3]; Price et al, [4]), DARPA's ATIS task (Price, [5]), the Texas Instruments continuous-digit recognition task (Leonard,[6]), and other small vocabulary recognition tasks.…”

Section: Decipher Tmmentioning

confidence: 99%

Performance of SRI's Decipher Speech Recognition System on DARPA's CSR Task

Murveit¹,

Butzberger²,

Weintraub³

1992

Self Cite

View full text Add to dashboard Cite

SRI has ported its DECIPHER TM speech recognition system from DARPA's ATIS domain to DARPA's CSR domain (read and spontaneous Wall Street Journal speech). This paper describes what needed to be done to port DECIPHER TM, and reports experiments performed with the CSR task.The system was evaluated on the speaker-independent (SI) portion of DARPA's February 1992 "Dry-Run" WSJ0 test and achieved 17.1% word error without verbalized punctuation (NVP) and 16.6% error with verbalized punctuation (VP). In addition, we increased the amount of training data and reduced the VP error rate to 12.9%. This SI error rate (with a larger amount of training data) equalled the best 600-training-sentence speaker-dependent error rate reported for the February CSR evaluation. Finally, the system was evaluated on the VP data using microphones unknown to the system instead of the training-set's Sennheiser microphone and the error rate only inere~ased to 26.0%.

show abstract

“…The physical structure and dimension of vocal tract as well as excitation source are unique for each speaker. The speech analysis deals with stages with suitable frame size for segmenting speech signal for further analysis and extracting [5]. The speech analysis is done with following three techniques.…”

Section: A Speech Analysismentioning

confidence: 99%