\Phi DM-Dialog: An Experimental Speech-to-Speech Dialog Translation System

Authors:
Hiroaki Kitano
Affiliations:
-
Venue:
Computer
Year:
1991

Citing 3
Cited 11

Readings in speech recognition

Readings in speech recognition
Inside Case-Based Reasoning

Inside Case-Based Reasoning
Parsing noisy sentences

COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2

SNAP: Parallel Processing Applied to AI

Computer
PALKA: a system for lexical knowledge acquisition

CIKM '93 Proceedings of the second international conference on Information and knowledge management
The IXM2 Parallel Associative Processor for AI

Computer
Acquisition of Linguistic Patterns for Knowledge-Based Information Extraction

IEEE Transactions on Knowledge and Data Engineering
SNAP: A Market-Propagation Architecture for Knowledge Processing

IEEE Transactions on Parallel and Distributed Systems
The SNAP-1 Parallel AI Prototype

IEEE Transactions on Parallel and Distributed Systems
Real-time spoken language translation using associative processors

ANLC '94 Proceedings of the fourth conference on Applied natural language processing
Semantic Network Array Processor as a massively parallel computing platform for high performance and large-scale natural language processing

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Challenges of massive parallelism

IJCAI'93 Proceedings of the 13th international joint conference on Artifical intelligence - Volume 1
High performance natural language processing on semantic network array processor

IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
Efficient grammar processing for a spoken language translation system

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1

Quantified Score

Hi-index	4.10

Visualization

Abstract

\Phi DM-Dialog, one of the first experimental speech-to-speech systems and the first to demonstrate simultaneous interpretation possibilities, is described. An overview is given of the model behind \Phi DM-Dialog. It consists of a memory network for representing various knowledge levels and markers for inferencing. The markers have rich information content. The integration of speech and natural language processing in \Phi DM-Dialog and its cost-based scheme of ambiguity resolution are discussed. Its simultaneous interpretation capability, which is made possible by an incremental parsing and generation algorithm, is examined. Prototype system results are reported.