A parallel architecture for signal understanding through inference on uncertain data
Volume I: Parallel architectures on PARLE: Parallel Architectures and Languages Europe
Large-vocabulary speaker-independent continuous speech recognition: the sphinx system
Large-vocabulary speaker-independent continuous speech recognition: the sphinx system
COLING '86 Proceedings of the 11th coference on Computational linguistics
Distributed memory: a basis for chart parsing
COLING '86 Proceedings of the 11th coference on Computational linguistics
Parsing spoken language: a semantic caseframe approach
COLING '86 Proceedings of the 11th coference on Computational linguistics
Divided and valency-oriented parsing in speech understanding
COLING '86 Proceedings of the 11th coference on Computational linguistics
The role of semantic processing in an automatic speech understanding system
COLING '86 Proceedings of the 11th coference on Computational linguistics
Robust parsing of severely corrupted spoken utterances
COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 1
A parallel-process model of on-line inference processing
IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 2
Parallel parsing for unification grammars
IJCAI'87 Proceedings of the 10th international joint conference on Artificial intelligence - Volume 2
Modified caseframe parsing for speech understanding systems
IJCAI'87 Proceedings of the 10th international joint conference on Artificial intelligence - Volume 2
A tabular method for island-driven context-free grammar parsing
AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 1
Efficient parallel CKY parsing on GPUs
IWPT '11 Proceedings of the 12th International Conference on Parsing Technologies
Hi-index | 0.00 |
This paper describes SYNAPSIS, a parser for performing real-time understanding of spoken utterances in a parallel computational environment. Understanding continuous speech allowing reasonably free syntax poses two main problems, namely the risk of erroneous interpretations and the largeness of the search space owing to the high uncertainty of the input. The parser is characterized by an approach whose major novel features are 1) a drastic reduction of idle time, thanks to the asynchronous inter agent communications, and 2) high modularity, thanks to the distribution of homogeneous pieces of knowledge rather than distribution of different parsing tasks. These features make the parser most apt for implementation on homogeneous Transputer-based distributed architectures.