Data input device, data input method, storage medium, and in-vehicle apparatus

• US 9,613,625 B2
• Filed: 02/10/2015
• Issued: 04/04/2017
• Est. Priority Date: 02/24/2014
• Status: Expired due to Fees

• Current Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Inventors: Kashimoto, Kazutoshi
• Primary Examiner(s): ROBERTS, SHAUN A
• Application Number:
  US14/618,214
• Publication Number:
  US 20150243277A1
• Time in Patent Office: 784 Days
• Field of Search: 704243, 704270, 704275
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/226 using non-speech characteristics
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A dynamic speech recognition dictionary generating unit extracts, from phrases stored in a speech recognition dictionary, phrases of which heads match a head of a character string inputted through a character string input unit and generates a dynamic speech recognition dictionary that stores difference phrases that are each part of an extracted phrase excluding a common phrase that is common among the extracted phrases. A speech recognition unit carries out recognition of a user utterance by using the dynamic speech recognition dictionary. An input character string confirming unit confirms an input character string candidate that includes a recognized difference phrase as an input character string.

Claims

1. A data input device that includes two inputs including a character string input that accepts a character string and a voice input that accepts voice input, a display that displays the character string, and a speech recognition dictionary, the data input device comprising:

a dynamic speech recognition dictionary generator which, in operation, extracts phrases of which heads match a head of the character string inputted through the character string input from phrases stored in the speech recognition dictionary, and generates a dynamic speech recognition dictionary that stores difference phrases, the difference phrases each being part of an extracted phrase excluding a common phrase that is common among the extracted phrases;

a display controller which, in operation, displays the difference phrases of an input character string candidate, the difference phrases being highlighted on the display and excluding the common phrase;

a speech recognizer which, in operation, carries out speech recognition of voice inputted through the voice input by using the dynamic speech recognition dictionary;

an input character string confirmer which, in operation, confirms the input character string candidate that includes a difference phrase recognized by the speech recognizer as an input character string; and

an input switcher which, in operation, switches between the character string input and the voice input based on a running state of a vehicle,

wherein, in a case of receiving a changed state of the vehicle from stopping to starting before a whole character string is finished inputting, the input switcher switches from the character string input to the voice input, the display controller displays the difference phrases of the input character string candidate with the common phrase that has already been confirmed by the character string input, the difference phrases being highlighted on the display, and the input character string confirmer confirms the input character string candidate using the highlighted difference phrase recognized by the speech recognizer as the input character string, and

at least one of the dynamic speech recognition dictionary generator, the display controller, the speech recognizer and the input character string confirmer is included in a processor.

2. The data input device according to claim 1,

wherein the speech recognizer carries out speech recognition by sequentially using the dynamic speech recognition dictionary and the speech recognition dictionary.

3. The data input device according to claim 1,

wherein the dynamic speech recognition dictionary generator generates the dynamic speech recognition dictionary each time a character is inputted through the character string input.

4. An in-vehicle apparatus, comprising:

the data input device according to claim 1.

5. A data input method for a data input device that includes a character string input that accepts a character string, a display that displays the character string, a voice input that accepts voice input, and a speech recognition dictionary, the data input method comprising:

extracting phrases of which heads match a head of the character string inputted through the character string input from phrases stored in the speech recognition dictionary, and generating a dynamic speech recognition dictionary that stores difference phrases, the difference phrases each being part of an extracted phrase excluding a common phrase that is common among the extracted phrases;

displaying the difference phrases of an input character string candidate, the difference phrases being highlighted on the display and excluding the common phrase;

carrying out speech recognition of voice inputted through the voice input by using the dynamic speech recognition dictionary;

confirming the input character string candidate that includes a difference phrase recognized through the speech recognition as an input character string; and

switching between the character string input and the voice input based on a running state of a vehicle,

wherein, in a case of receiving a changed state of the vehicle from stopping to starting before a whole character string is finished inputting, the character string input is switched to the voice input, the difference phrases of the input character string candidate are displayed with the common phrase that has already been confirmed by the character string input, the difference phrases being highlighted on the display, and the input character string candidate is confirmed using the highlighted difference phrase recognized through the speech recognition as the input character string.

6. A non-transitory, tangible computer-readable storage medium storing a program for a data input device that includes a character string input that accepts a character string, a display that displays the character string, a voice input that accepts voice input, and a speech recognition dictionary, the program, when executed by a computer, causing the computer to perform operations comprising:

extracting phrases of which heads match a head of the character string inputted through the character string input from phrases stored in the speech recognition dictionary, and generating a dynamic speech recognition dictionary that stores difference phrases, the difference phrases each being part of an extracted phrase excluding a common phrase that is common among the extracted phrases;

displaying the difference phrases of an input character string candidate, the difference phrases being highlighted on the display and excluding the common phrase;

carrying out speech recognition of voice inputted through the voice input by using the dynamic speech recognition dictionary;

confirming the input character string candidate that includes a difference phrase recognized through the speech recognition as an input character string; and

switching between the character string input and the voice input based on a running state of a vehicle,

wherein, in a case of receiving a changed state of the vehicle from stopping to starting before a whole character string is finished inputting, the character string input is switched to the voice input, the difference phrases of the input character string candidate are displayed with the common phrase that has already been confirmed by the character string input, the difference phrases being highlighted on the display, and the input character string candidate is confirmed using the highlighted difference phrase recognized through the speech recognition as the input character string.