Information terminal, server device, searching system, and searching method thereof

• US 8,903,651 B2
• Filed: 09/21/2012
• Issued: 12/02/2014
• Est. Priority Date: 09/22/2011
• Status: Active Grant

• Current Assignee: Clarion Co., Ltd. (Faurecia SA)
• Original Assignee: Clarion Co., Ltd. (Faurecia SA)
• Inventors: Fukunaga, Kouichirou, Watarai, Norio, Motohashi, Masataka, Obuchi, Yasunari, Homma, Takeshi
• Primary Examiner(s): Cheung, Mary
• Assistant Examiner(s): Trivedi, Atul
• Application Number:
  US13/624,071
• Publication Number:
  US 20130080056A1
• Time in Patent Office: 802 Days
• Field of Search: 701/419, 701427-428, 701/431, 701/441, 701/443, 701/488, 701/539
• US Class Current: 701/427
• CPC Class Codes: G01C 21/3476 using point of interest [POI] information, e.g. a route passing visible POIs
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G01C 21/3679 Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities G01C21/3611 takes precedence
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 19/0018 Speech coding using phonetic or linguistical decoding of the source; Reconstruction using text-to-speech synthesis
• CPC Class Codes: G10L 19/24 Variable rate codecs, e.g. for generating different qualities using a scalable representation such as hierarchical encoding or layered encoding
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 25/60 for measuring the quality of voice signals

Abstract

An object of the present invention is to provide a technique of an information terminal that allows more efficient utilization of high-level searching functions. The information terminal is provided with an audio input accepting unit to accept an input of speech information, a communication unit to establish communication with a predetermined server device via a network, an output unit, a POI specifying unit to transmit the speech information accepted by the audio input accepting unit to the server device and receive information specifying a candidate of a POI (Point Of Interest) associated with the speech information, a POI candidate output unit to output to the output unit, the information specifying the candidate of the POI received by the POI specifying unit, and a route searching unit to accept a selective input of the information specifying the candidate of the POI, and search for a route directed to the POI.

Claims

1. A server device comprising:

a speech information receiver adapted to receive speech information from a predetermined information terminal via a network;

a noise removal processor adapted to remove noise information from the speech information, the noise removal processor configured to apply multiple noise removal algorithms to create multiple speech information items from which the noise has been removed;

a speech information transmitter adapted to transmit the speech information items from which the noise has been removed to a predetermined speech recognizer via the network;

a character string receiver adapted to receive, via the network, a plurality of character string candidates as a result of recognition of the speech information items by the speech recognizer;

a character string transmitter adapted to transmit a plurality of character string candidates, via the network, to a predetermined POI provider for providing POI (Point of Interest) information associated with the character string candidate, the character string transmitter configured;

i) to assign weights to the plurality of character string candidates depending on the noise removal algorithms previously applied to each corresponding speech information item; and

ii) based on the selected application of noise removal algorithms to each speech information item, to give greater importance to corresponding character string candidates considered as having relatively high recognition precision;

a POI information receiver adapted to receive, via the network, the POI information associated with the character string; and

a POI information transmitter adapted to transmit the POI information to the information terminal.

2. The server device according to claim 1, wherein the server device further comprises:

a character string candidate transmitter adapted to transmit multiple character string candidates to the information terminal; and

a selected character string receiver adapted to receive from the information terminal one selected character string candidate selected from the multiple character string candidates;

wherein the character string candidate transmitter is configured to transit, via the network, said selected one character string candidate to the POI provider.

3. The server device according to claim 1, wherein,

when multiple character string candidates are included as the character string received by the character string receiver, the character string transmitter is configured to transmit the multiple character string candidates to the POI provider via the network, and

the POI information receiver is configured to receive multiple POI information items being associated with the multiple character string candidates, respectively.

4. The server device according to claim 1, further comprising a redundancy elimination device adapted to eliminate redundancy of POI by selectively integrating together received redundant character string candidates to produce an integrated candidate having an associated higher degree of accuracy, the higher degree of accuracy of the integrated candidate allowing ranking of the integrated candidate relative to other character string candidates received by the server device from the speech recognizer.

5. The server device according to claim 1, wherein,

when the speech information receiver starts receiving the speech information from the predetermined information terminal via the network, the noise removal processor is configured to remove the noise information sequentially from the speech information being received, and

the speech information transmitter is configured to transmit the speech information items, from which the noise removal processor has removed the noise, sequentially to the predetermined speech recognizer via the network.

6. A searching system having an information terminal and a server device communicating with the information terminal via a network, wherein the information terminal comprises:

an audio receiver adapted to accept an input of speech information;

a communication device adapted to establish communication with the server device via the network;

an output device;

a POI specifying device adapted to transmit the speech information accepted by the audio receiver to the server device, and receiving information specifying a candidate of a POI (Point Of Interest) associated with the speech information,

a POI candidate output device adapted to output to the output device, the information specifying the candidate of the POI received by the POI specifying unit, and

a route searching device adapted to accept a selective input of the information specifying the candidate of the POI, and search for a route directed to the POI, and

wherein the server device includes

a speech information receiver adapted to receive speech information from a predetermined information terminal via a network;

a noise removal processor adapted to remove noise information from the speech information, the noise removal processor configured to apply multiple noise removal algorithms to create multiple speech information items from which the noise has been removed;

a speech information transmitter adapted to transmit the speech information items from which the noise has been removed to a predetermined speech recognizer via the network;

a character string receiver adapted to receive, via the network, a plurality of character string candidates as a result of recognition of the speech information items by the speech recognizer;

a character string transmitter adapted to transmit a plurality of character string candidates, via the network, to a predetermined POI provider for providing POI (Point of Interest) information associated with the character string candidate, the character string transmitter configured;

i) to assign weights to the plurality of character string candidates depending on the noise removal algorithms previously applied to each corresponding speech information item; and

ii) based on the selected application of noise removal algorithms to each speech information item, to give greater importance to corresponding character string candidates considered as having relatively high recognition precision;

a POI information receiver adapted to receive, via the network, the POI information associated with the character string; and

a POI information transmitter adapted to transmit the POI information to the information terminal.

7. A searching method of a searching system having an information terminal and a server device communicating with the information terminal via a network, the searching system comprising an audio receiver adapted to accept an input of speech information and an output device, and the searching method executing:

a transmitting step of transmitting the speech information accepted by the audio receiver to the server device;

a speech information receiving step of receiving, via the network, the speech information from the information terminal;

a noise removing step of removing noise information from the speech information, the noise removing step applying multiple noise removal algorithms to create multiple speech information items from which the noise has been removed;

a speech information transmitting step of transmitting, via the network, the speech information from which the noise has been removed to a predetermined speech recognizer;

a POI information receiving step of receiving, via the network from a predetermined POI provider, POI (Point Of Interest) information associated with the speech information transmitted to the speech recognizer,

a POI information transmitting step of transmitting the POI information to the information terminal;

a POI specifying step of receiving the POI information; and

a POI candidate outputting step of outputting to the output device, the POI information received by the POI specifying step;

the method further including;

at a character string receiver in the server device, receiving, via the network, a plurality of character string candidates resulting from the recognition of the speech information items by the predetermined speech recognizer; and

at a character string transmitter adapted to transmit a plurality of selected character string candidates, via the network, to the predetermined POI provider,

i) assigning weights to a plurality of character string candidates depending on the noise removal algorithms previously applied to each corresponding speech information item; and

ii) based on the selected application of noise removal algorithms to each speech information item, giving greater importance to corresponding character string candidates considered as having relatively high recognition precision.

8. The searching method of claim 7, wherein the server device further comprises:

a character string candidate transmitter adapted to transmit multiple character string candidates to the information terminal; and

a selected character string receiver adapted to receive from the information terminal one selected character string candidate selected from the multiple character string candidates;

wherein the character string candidate transmitter is configured to transit, via the network, said selected one character string candidate to the POI provider.

9. The searching method of claim 7, wherein,

when multiple character string candidates are included as the character string received by the character string receiver, the character string transmitter is configured to transmit the plurality of character string candidates to the POI provider via the network, and

the POI information receiver is configured to receive multiple POI information items being associated with the multiple character string candidates, respectively.

10. The searching method of claim 7, further comprising eliminating redundancy of POI by selectively integrating together received redundant character string candidates to produce an integrated candidate having an associated higher degree of accuracy, the higher degree of accuracy of the integrated candidate allowing ranking of the integrated candidate relative to other character string candidates received by the server device from the speech recognizer.

11. The searching method of claim 7, wherein the noise removal processor uses multiple noise removing algorithms to create multiple speech information items from which the noise has been removed.

12. The searching method of claim 7, wherein,

when the speech information receiver starts receiving the speech information from the predetermined information terminal via the network, a noise removal processor is configured to remove the noise information sequentially from the speech information being received, and

the speech information transmitter is configured to transmit the speech information items, from which the noise removal processor has removed the noise, sequentially to the predetermined speech recognizer via the network.