VOICE RECOGNITION APPARATUS

• US 20130166290A1
• Filed: 12/13/2012
• Published: 06/27/2013
• Est. Priority Date: 12/26/2011
• Status: Active Grant

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: SUZUKI, Ryuichi
• Granted Patent: US 9,123,327 B2
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A voice recognition apparatus includes a command recognizer and a data recognizer. The command recognizer recognizes a command portion of a voice input and outputs a command based on a voice recognition result of the voice input. The data recognizer recognizes a data portion of a voice inputs and outputs a data based on a voice recognition result of the voice input. The data recognizer further includes a plurality of data-category recognizers respectively using a data-category dictionary for recognizing the data portion of the voice input and outputting a data result. A voice recognition result selection unit of the voice recognition apparatus selects one of the data results from the data-category recognizers based on the command recognized by the command recognizer.

Claims

1. A voice recognition apparatus comprising:

a voice input unit inputting a voice in a continuous manner as a voice input, the voice input including a command portion and a data portion;

a command recognizer recognizing the command portion of the voice input and outputting a command based on a voice recognition result of the voice input with reference to a command dictionary;

a data recognizer recognizing the data portion of the voice input and outputting a data recognition result based on a voice recognition result of the voice input with reference to a data dictionary, the data dictionary including a plurality of data-category dictionaries corresponding to a plurality of data categories, and the data recognizer including a plurality of data-category recognizers respectively using one of the plurality of data-category dictionaries for recognizing the data portion of the voice input and outputting the data recognition result; and

a voice recognition result selection unit selecting one of a plurality of data recognition results provided by the plurality of data-category recognizers, as a most suitable voice recognition result, based on the command provided by the command recognizer.

2. The voice recognition apparatus of claim 1, wherein

the voice recognition result selection unit selects the command from the command recognizer as the most suitable voice recognition result when none of the data recognition results from the plurality of data-category recognizers is suitable.

3. The voice recognition apparatus of claim 1, wherein

the command recognizer and the plurality of data-category recognizers of the data recognizer simultaneously perform respective voice recognition processes.

4. The voice recognition apparatus of claim 1, wherein

the plurality of data-category dictionaries are an address dictionary, a music piece dictionary, and a phonebook dictionary, and

the plurality of data-category recognizers are an address recognizer, a music piece recognizer, and a phonebook recognizer.

5. The voice recognition apparatus of claim 4, wherein

the voice recognition result selection unit selects the data recognition result of an address by the address recognizer when the command recognized by the command recognizer is an address related command,

the voice recognition result selection unit selects the data recognition result of a music piece by the music piece recognizer when the command recognized by the command recognizer is a music piece related command, and

the voice recognition result selection unit selects the data recognition result of a phonebook by the phonebook recognizer when the command recognized by the command recognizer is a telephone related command.