Structure for Grammar and Dictionary Representation in Voice Recognition and Method for Simplifying Link and Node-Generated Grammars

• US 20110191107A1
• Filed: 02/18/2011
• Published: 08/04/2011
• Est. Priority Date: 05/20/2005
• Status: Active Grant

• Current Assignee: Sony Interactive Entertainment Inc. (Sony Group Corp.)
• Original Assignee: Sony Computer Entertainment Incorporated (Sony Group Corp.)
• Inventors: Chen, Ruxin, Abrego, Gustavo Hernandez
• Granted Patent: US 8,190,433 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 15/285 Memory allocation or algorithm optimisation to reduce hardware requirements

Abstract

A speech recognition engine is provided with an acoustic model and a layered grammar and dictionary library. The layered grammar and dictionary library includes a language and non-grammar layer that supplies types of rules a grammar definition layer can use and defines non-grammar the speech recognition engine should ignore. The layered grammar and dictionary library also includes a dictionary layer that defines phonetic transcriptions for word groups the speech recognition engine is meant to recognize when voice input is received. The layered grammar and dictionary library further includes a grammar definition layer that applies rules from the language and non-grammar layer to define combinations of word groups the speech recognition system is meant to recognize. Voice input is received at a speech recognition engine and is processed using the acoustic model and the layered grammar and dictionary library.

Claims

1. A method for operating a speech recognition system, the method comprising:

(a) receiving voice input at a speech recognition engine;

(b) receiving an acoustic model at the speech recognition engine;

(c) providing a layered grammar and dictionary library to the speech recognition engine, the layered grammar and dictionary library including,

(i) defining a language and non-grammar layer that supplies types of rules a grammar definition layer can use and defines non-grammar the speech recognition system should ignore;

(ii) defining a dictionary layer that defines phonetic transcriptions for word groups the speech recognition system is meant to recognize when the voice input is received;

(iii) defining a grammar definition layer that applies rules from the language and non-grammar layer to define combinations of word groups the speech recognition system is meant to recognize when the voice input is received;

(d) using the acoustic model and the layered grammar and dictionary library to process the voice input.

2. A method for operating a speech recognition system as recited in claim 1, wherein the language and non-grammar layer are defined by one or more character combinations, and the one or more character combinations are used to define the rules.

3. A method for operating a speech recognition system as recited in claim 1, wherein the word groups of the dictionary layer are defined in accordance with a generic group listing or a grammar related group.

4. A method for operating a speech recognition system as recited in claim 1, wherein the combinations of word groups are listed with the applied rules so as to define recognizable phrases when the voice input is received.

5. A method for operating a speech recognition system as recited in claim 1, wherein the combinations of word groups are automatically generated using a single rule, the single rule interconnecting the combinations of word groups in a listing, and the listing defining the grammar definition layer.

6. A method for operating a speech recognition system as recited in claim 1, wherein the combinations of word groups are user generated using one or more of the applied rules, the one or more of the applied rules interconnecting the combinations of word groups in a listing, and the listing defining the grammar definition layer.

7. A method for operating a speech recognition system as recited in claim 1, wherein the voice input is used to control interactivity with a computer system.

8. A method for operating a speech recognition system as recited in claim 1, wherein the computer system is a gaming computing device.

9. A method for operating a speech recognition system as recited in claim 1, wherein the voice input is associated with a computing event that includes one or more of computer assisted voice communication, computer triggered voice gaming commands, computer voice assisted gaming, and computer triggered voice commands.

10. A method for operating a speech recognition system as recited in claim 1, further comprising:

optimizing the grammar definition layer by,

defining a set of phrases corresponding to the combinations of word groups the speech recognition system is meant to recognize,

defining each of the set of phrases in a node and link structure, wherein a given node is defined by one or more words, and wherein a given link connects the one or more words of one node to the one or more words of another node,

identifying redundant nodes by examining the node and link structures of each of the set of phrases so as to generate and substitute a single node for the redundant nodes, wherein redundant nodes are defined by identical words, and wherein each of the redundant nodes has a respective outgoing link to a same successor node,

examining the node and link structures to identify nodes that are capable of being vertically grouped and grouping the identified nodes to define vertical word groups, and

fusing horizontally linked nodes of the set of phrases that are not vertically grouped and that represent a single sentence path into fused word groups, wherein the vertical word groups and the fused word groups are linked to define an optimized grammar structure.

11. A method for operating a speech recognition system as recited in claim 10, wherein the node and link structure of the set of phrases includes a single node or multiple nodes connected by a directional link that indicates a progression of the nodes of a particular one of the set of phrases.

12. A method for operating a speech recognition system as recited in claim 10, wherein a plurality of nodes are capable of being vertically grouped when each of the plurality of nodes is linked to both a same predecessor and a same successor node.

13. A method for operating a speech recognition system as recited in claim 10, wherein fusing horizontally linked nodes includes generating and substituting a single multi-word node for the fused horizontally linked nodes.

14. A method for operating a speech recognition system as recited in claim 13, wherein a first node is fused with a second node when,

the first node is horizontally linked to the second node, and

each of the first and second nodes has a respective word count of one, and

the first node is the only predecessor node to which the second node is horizontally linked, and

the second node is the only successor node to which the first node is horizontally linked, and

the first node has only one predecessor node horizontally linked to itself.

15. A data storage device for storing data to be read by a computer system including program instructions for operating a speech recognition system, comprising:

(a) program instructions for receiving voice input at a speech recognition engine;

(b) program instructions for receiving an acoustic model at the speech recognition engine;

(c) program instructions for defining a layered grammar and dictionary library to the speech recognition engine, the layered grammar and dictionary library including,

(i) a language and non-grammar layer that supplies types of rules a grammar definition layer can use and defines non-grammar the speech recognition system should ignore,

(ii) a dictionary layer that defines phonetic transcriptions for word groups the speech recognition system is meant to recognize when the voice input is received,

(iii) a grammar definition layer that applies rules from the language and non-grammar layer to define combinations of word groups the speech recognition system is meant to recognize when the voice input is received; and

(d) program instructions for using the acoustic model and the layered grammar and dictionary library to process the voice input.

16. A data storage device for storing data to be read by a computer system including program instructions for operating a speech recognition system as recited in claim 15, wherein the language and non-grammar layer are defined by one or more character combinations, and the one or more character combinations are used to define the rules.

17. A data storage device for storing data to be read by a computer system including program instructions for operating a speech recognition system as recited in claim 15, wherein the word groups of the dictionary layer are defined in accordance with a generic group listing or a grammar related group.

18. A data storage device for storing data to be read by a computer system including program instructions for operating a speech recognition system as recited in claim 15, wherein the combinations of word groups are listed with the applied rules so as to define recognizable phrases when the voice input is received.

19. A data storage device for storing data to be read by a computer system including program instructions for operating a speech recognition system as recited in claim 15, wherein the combinations of word groups are automatically generated using a single rule, the single rule interconnecting the combinations of word groups in a listing, and the listing defining the grammar definition layer.

20. A data storage device for storing data to be read by a computer system including program instructions for operating a speech recognition system as recited in claim 15, wherein the combinations of word groups are user generated using one or more of the applied rules, the one or more of the applied rules interconnecting the combinations of word groups in a listing, and the listing defining the grammar definition layer.