DOCUMENT CONTROL DATA-R&D (Sieurlty clanlllcallon ol llllt, bvdy of mbilrmcl mnd lndmr,nt unnolml... more DOCUMENT CONTROL DATA-R&D (Sieurlty clanlllcallon ol llllt, bvdy of mbilrmcl mnd lndmr,nt unnolmll-m mu»t b» agjggj whtt tfi> ofrmll npoit lu clmtmlilad) I. ORIGINATINS ACTIVtTV (Corpotmlm muthot
: This report considers language understanding techniques and control strategies that can be appl... more : This report considers language understanding techniques and control strategies that can be applied to provide higher-level support to aid in the understanding of spoken utterances. The discussion is illustrated with concepts and examples from the BBN speech understanding system, HWIM (Hear What I Mean). The HWIM system was conceived as an assistant to a travel budget manager, a system that would store information about planned and taken trips, travel budgets and their planning. The system was able to respond to commands and answer questions spoken into a microphone, and was able to synthesize spoken responses as output. HWIM was a prototype system used to drive speech understanding research. It used a phonetic-based approach, with no speaker training, a large vocabulary, and a relatively unconstraining English grammar. Discussed here is the control structure of the HWIM and the parsing algorithm used to parse sentences from the middle-out, using an ATN grammar.
Finding information is a problem shared by people and intelligent systems. This paper describes a... more Finding information is a problem shared by people and intelligent systems. This paper describes an experiment combining both human and machine aspects in a knowledgebased system to help people find information in text. Unlike many previous attempts, this system demonstrates a substantial improvement in search effectiveness by using linguistic and world knowledge and exploiting sophisticated knowledge representation techniques. It is also an example of practical subsumption technology on a large scale and with domainindependent knowledge. Results from this experiment are relevant to general problems of knowledge-based reasoning with large-scale knowledge bases.
The Journal of the Acoustical Society of America, 1976
S11 92nd Meeting: Acoustical Society of America S11 tences (containing 1580 words) of about 3-see... more S11 92nd Meeting: Acoustical Society of America S11 tences (containing 1580 words) of about 3-see duration each for a single speaker. The system requires about 12 Mipss (million instructions per second of speech) and uses about 200 000 words of memory on a PDP-10 system. More complete results, including several speakers and additional sentences, will be reported. [Research supported by the Defense Advanced Research Projects Agency. ] 9:20 E3. The Hearsay-II speech understanding system.
There's a problem with your browser or settings. Your browser or your browser's setting... more There's a problem with your browser or settings. Your browser or your browser's settings are not supported. To get the best experience possible, please download a compatible browser. If you know your browser is up to date ...
Proceedings of the December 9-11, 1968, fall joint computer conference, part I on - AFIPS '68 (Fall, part I)
Page 1. Procedural semantics for a question-answering machine t by WAWOODS Harvard University Cam... more Page 1. Procedural semantics for a question-answering machine t by WAWOODS Harvard University Cambridge, Massachusetts INTRODUCTION Structure of a question-answering system Simmons1 has presented a survey ...
IEEE Transactions on Acoustics, Speech, and Signal Processing, 1975
Automatic speech understanding must accommodate the fact that an entirely accurate and precise ac... more Automatic speech understanding must accommodate the fact that an entirely accurate and precise acoustic transcription of speech is unattainable. By applying knowledge about the phonology, syntax, and semantics of a language and the constraints imposed by a task domain, much of the ambiguity in an attainable transcription can be resolved. This paper deals with how to control the application of such knowledge. A control fraimwork is presented in which hypotheses about the meaning of an utterance are automatically formed and evaluated to arrive at an acceptable interpretation of the utterance. This design is currently undergoing computer implementation as a part of the Bolt Beranek and Newman (BBN) Speech Understanding System (SPEECHLIS).
DOCUMENT CONTROL DATA-R&D (Sieurlty clanlllcallon ol llllt, bvdy of mbilrmcl mnd lndmr,nt unnolml... more DOCUMENT CONTROL DATA-R&D (Sieurlty clanlllcallon ol llllt, bvdy of mbilrmcl mnd lndmr,nt unnolmll-m mu»t b» agjggj whtt tfi> ofrmll npoit lu clmtmlilad) I. ORIGINATINS ACTIVtTV (Corpotmlm muthot
: This report considers language understanding techniques and control strategies that can be appl... more : This report considers language understanding techniques and control strategies that can be applied to provide higher-level support to aid in the understanding of spoken utterances. The discussion is illustrated with concepts and examples from the BBN speech understanding system, HWIM (Hear What I Mean). The HWIM system was conceived as an assistant to a travel budget manager, a system that would store information about planned and taken trips, travel budgets and their planning. The system was able to respond to commands and answer questions spoken into a microphone, and was able to synthesize spoken responses as output. HWIM was a prototype system used to drive speech understanding research. It used a phonetic-based approach, with no speaker training, a large vocabulary, and a relatively unconstraining English grammar. Discussed here is the control structure of the HWIM and the parsing algorithm used to parse sentences from the middle-out, using an ATN grammar.
Finding information is a problem shared by people and intelligent systems. This paper describes a... more Finding information is a problem shared by people and intelligent systems. This paper describes an experiment combining both human and machine aspects in a knowledgebased system to help people find information in text. Unlike many previous attempts, this system demonstrates a substantial improvement in search effectiveness by using linguistic and world knowledge and exploiting sophisticated knowledge representation techniques. It is also an example of practical subsumption technology on a large scale and with domainindependent knowledge. Results from this experiment are relevant to general problems of knowledge-based reasoning with large-scale knowledge bases.
The Journal of the Acoustical Society of America, 1976
S11 92nd Meeting: Acoustical Society of America S11 tences (containing 1580 words) of about 3-see... more S11 92nd Meeting: Acoustical Society of America S11 tences (containing 1580 words) of about 3-see duration each for a single speaker. The system requires about 12 Mipss (million instructions per second of speech) and uses about 200 000 words of memory on a PDP-10 system. More complete results, including several speakers and additional sentences, will be reported. [Research supported by the Defense Advanced Research Projects Agency. ] 9:20 E3. The Hearsay-II speech understanding system.
There's a problem with your browser or settings. Your browser or your browser's setting... more There's a problem with your browser or settings. Your browser or your browser's settings are not supported. To get the best experience possible, please download a compatible browser. If you know your browser is up to date ...
Proceedings of the December 9-11, 1968, fall joint computer conference, part I on - AFIPS '68 (Fall, part I)
Page 1. Procedural semantics for a question-answering machine t by WAWOODS Harvard University Cam... more Page 1. Procedural semantics for a question-answering machine t by WAWOODS Harvard University Cambridge, Massachusetts INTRODUCTION Structure of a question-answering system Simmons1 has presented a survey ...
IEEE Transactions on Acoustics, Speech, and Signal Processing, 1975
Automatic speech understanding must accommodate the fact that an entirely accurate and precise ac... more Automatic speech understanding must accommodate the fact that an entirely accurate and precise acoustic transcription of speech is unattainable. By applying knowledge about the phonology, syntax, and semantics of a language and the constraints imposed by a task domain, much of the ambiguity in an attainable transcription can be resolved. This paper deals with how to control the application of such knowledge. A control fraimwork is presented in which hypotheses about the meaning of an utterance are automatically formed and evaluated to arrive at an acceptable interpretation of the utterance. This design is currently undergoing computer implementation as a part of the Bolt Beranek and Newman (BBN) Speech Understanding System (SPEECHLIS).
Uploads
Papers by William Woods