Large vocabulary connected speech recognition system and method of language representation using evolutional grammar to represent context free grammars

• US 5,699,456 A
• Filed: 01/21/1994
• Issued: 12/16/1997
• Est. Priority Date: 01/21/1994
• Status: Expired due to Fees

• Current Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Brown, Michael Kenneth, Glinski, Stephen Charles
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): Tadayon, Bijan
• Application Number:
  US08/184,811
• Time in Patent Office: 1,425 Days
• Field of Search: 382/155, 382/156, 382/173, 382/181, 382/185, 382/186, 382/187, 382/188, 382/189, 382/190, 382/192, 382/195, 382/199, 382/201, 382/202, 382/203, 382/209, 382/217, 382/224, 382/226, 382/227, 382/228, 382/229, 382/230, 382/231, 382/232, 382/254, 382/266, 382/270, 382/191, 382/193, 382/194, 382/196, 382/197, 382/205, 382/210, 382/215 , 382/216, 382/218, 382/220, 382/271, 382/272, 382/273, 382/172, 395/2.55, 395/2.5, 395/2, 395/2.09, 395/2.61, 395/2.42, 395/2.64, 395/2.52
• US Class Current: 382/226
• CPC Class Codes: G06F 18/29 Graphical models, e.g. Bayesian networks
• CPC Class Codes: G06V 30/347 Sampling; Contour coding; Stroke extraction
• CPC Class Codes: G06V 30/373 using a special pattern or subpattern alphabet
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks

Abstract

A method of recognizing speech input selectively creates and maintains grammar representations of the speech input in essentially real time. Speech input frames received by a speech recognition system. Grammar representations are created for each speech frame and a probability score is derived for the representations indicating the probability of the accuracy of the representations to the speech input. Representations having a probability score below a predetermined threshold are not maintained. Those grammar representations having probability scores above predetermined threshold are maintained. As more speech frames are received by the system, additional grammar representations are created and the probability scores are updated. When the entire speech input has been received, the chain of grammar representations having the highest probability score is identified as the speech input.

Claims

1. A method for use in a grammar-based recognition system having a grammar represented by a grammar network comprised of arcs interconnecting nodes, ones of the arcs being terminal arcs representative of respective recognition models and others of the arcs being non-terminal arcs representing respective grammar sub-networks, each of the arcs having a source node and a destination node, and in which feature scores are input to the grammar network and resulting cumulative hypothesis scores are propagated through the models to produce cumulative hypothesis scores at various ones of the nodes, the method comprising the steps of

defining a first transition network having at least one non-terminal arc,

in response to the appearance of a hypothesis score meeting a predetermined turn-on criterion at the source node of a non-terminal arc, recursively replacing that non-terminal arc with transition networks until all of the arcs emanating from said source node are terminal arcs, and

instantiating the recognition models represented by all of the arcs emanating from said source node.

2. The invention of claim 1 wherein the recognition models represented by each of the terminal arcs of the network producing one or more recognition parameters and wherein the method comprises the further step of ceasing to propagate a hypothesis score through an individual one of said recognition models if said parameters satisfy a predetermined turn-off criterion.

3. The invention of claim 2 wherein said predetermined turn-on criterion is the attainment of a predetermined turn-on value by the cumulative hypothesis score at said source node.

4. The invention of claim 3 wherein said parameters are respective internal cumulative hypothesis scores and wherein said predetermined turn-off criterion is that all of those scores fall below a predetermined turn-off threshold.