Patent · US10395653B2 · B2 · US
Voice dialog device and voice dialog method
- (11) Publication number
- US10395653B2
- (21) Application number
- 15/598,504
- (22) Filing date
- 2017-05-18
- (30) Priority date
- 2016-05-27
- (43) Publication date
- 2019-08-27
- (45) Date of grant
- 2019-08-27
- (52) CPC
- G10L Speech analysis techniques or speech synthesis; speech recognition; speech or voice processing techniques; speech or audio coding or decoding: 15/22, 15/02, 15/08, 15/24, 2015/223, 2015/227, 25/78
- G06F Electric digital data processing: 2203/0381, 3/013, 3/0304, 3/167
- G06K Graphical data reading; presentation of data; record carriers; handling record carriers: 9/00255, 9/00281, 9/00604, 9/0061
- G06V Image or video recognition or understanding: 40/166, 40/171, 40/19, 40/193
- (73) Assignee
- TOYOTA MOTOR CO LTD
- (54) Title
- Voice dialog device and voice dialog method
- (57) Abstract
A voice dialog device, comprises a sight line detection unit configured to detect a sight line of a user; a voice processing unit configured to obtain voice pronounced by the user and a result of recognizing the voice; a dialog determination unit configured to determine whether or not the voice dialog device has a dialog with the user; and an answer generation unit configured to generate an answer, based on a result of recognizing the voice, wherein the dialog determination unit determines whether or not the user has started the dialog, based on both the sight line of the user and the obtained voice.
- Full text
- View on Google Patents
Claims (4)
- A voice dialog device, comprising: a sight line detection unit configured to detect a sight line of a user; a state determination unit configured to determine a state of the user; a voice processing unit configured to obtain voice pronounced by the user and a result of recognizing the voice; a dialog determination unit configured to determine whether or not the voice dialog device has a dialog with the user; and an answer generation unit configured to generate an answer, based on a result of recognizing the voice, wherein the dialog determination unit determines whether or not the user has started the dialog, based on both the sight line of the user and the obtained voice by: when the determined state of the user is driving a vehicle, the detected sight line of the user is in a vehicle forward direction, and a start keyword has been detected from the voice, the dialog determination unit determines that the user has started a dialog, when the determined state of the user is driving a vehicle and either the detected sight line of the user is not in the vehicle forward direction or the start keyword has not been detected from the voice, the dialog determination unit determines that the user has not started a dialog, when the determined state of the user is not driving a vehicle, the detected sight line of the user is in a direction toward the voice dialogue device, and a start keyword has been detected from the voice, the dialog determination unit determines that the user has started a dialog, and when the determined state of the user is not driving a vehicle and either the detected sight line of the user is not in the direction toward the voice dialogue device or the start keyword has not been detected from the voice, the dialog determination unit determines that the user has not started a dialog.
- The voice dialog device according to claim 1, wherein when the voice dialog device has the dialog with the user and a termination keyword has been detected from the voice, the dialog determination unit determines that the dialog has been terminated.
- A voice dialog method performed by a voice dialog device, comprising: a sight line detecting step of detecting a sight line of a user; a state determining step of determining a state of the user; a voice processing step of obtaining voice pronounced by the user and a result of recognizing the voice; a dialog determining step of determining whether or not the voice dialog device has a dialog with the user; and an answer generating step of generating an answer, based on a result of recognizing the voice, wherein, the dialog determining step includes determining whether or not the user has started the dialog based on both the sight line of the user and the obtained voice by: when state of the user determined by the state determining step is driving a vehicle, the sight line of the user detected by the sight line detecting step is in a vehicle forward direction, and a start keyword has been detected from the voice by the voice processing step, the dialog determining step determines that the user has started a dialog, when the state of the user determined by the state determining step is driving a vehicle and either the sight line of the user detected by the sight line detecting step is not in the vehicle forward direction or the start keyword has not been detected from the voice by the voice processing step, the dialog determining step determines that the user has not started a dialog, when the state of the user determined by the state determining step is not driving a vehicle, the sight line of the user detected by the sight line detecting step is in a direction toward the voice dialogue device, and a start keyword has been detected from the voice by the voice processing step, the dialog determining step determines that the user has started a dialog, and when the state of the user determined by the state determining step is not driving a vehicle and either the sight line of the user detected by the sight line detecting step is not in the direction toward the voice dialogue device or the start keyword has not been detected from the voice, the start keyword has not been detected from the voice by the voice processing step, the dialog determining step determines that the user has not started a dialog.
- A non-transitory computer readable storing medium recording a computer program for causing a computer to perform the voice dialog method according to claim 3.
Citations (15)
- JP2006272471A
- JP2007181888A
- JP2015013351A
- JPH0883093A
- US2003154084A1
- US2011106531A1
- US2012295708A1
- US2014350942A1
- US2015062168A1
- US2015109191A1
- US2017162197A1
- US2017270924A1
- US6076061A
- US8854303B1
- US9418653B2
Record as JSON
{
"publication_number": "US10395653B2",
"country": "US",
"kind": "B2",
"title": "Voice dialog device and voice dialog method",
"abstract": "A voice dialog device, comprises a sight line detection unit configured to detect a sight line of a user; a voice processing unit configured to obtain voice pronounced by the user and a result of recognizing the voice; a dialog determination unit configured to determine whether or not the voice dialog device has a dialog with the user; and an answer generation unit configured to generate an answer, based on a result of recognizing the voice, wherein the dialog determination unit determines whether or not the user has started the dialog, based on both the sight line of the user and the obtained voice.",
"claims": [
"1. A voice dialog device, comprising: a sight line detection unit configured to detect a sight line of a user; a state determination unit configured to determine a state of the user; a voice processing unit configured to obtain voice pronounced by the user and a result of recognizing the voice; a dialog determination unit configured to determine whether or not the voice dialog device has a dialog with the user; and an answer generation unit configured to generate an answer, based on a result of recognizing the voice, wherein the dialog determination unit determines whether or not the user has started the dialog, based on both the sight line of the user and the obtained voice by: when the determined state of the user is driving a vehicle, the detected sight line of the user is in a vehicle forward direction, and a start keyword has been detected from the voice, the dialog determination unit determines that the user has started a dialog, when the determined state of the user is driving a vehicle and either the detected sight line of the user is not in the vehicle forward direction or the start keyword has not been detected from the voice, the dialog determination unit determines that the user has not started a dialog, when the determined state of the user is not driving a vehicle, the detected sight line of the user is in a direction toward the voice dialogue device, and a start keyword has been detected from the voice, the dialog determination unit determines that the user has started a dialog, and when the determined state of the user is not driving a vehicle and either the detected sight line of the user is not in the direction toward the voice dialogue device or the start keyword has not been detected from the voice, the dialog determination unit determines that the user has not started a dialog.",
"2. The voice dialog device according to claim 1, wherein when the voice dialog device has the dialog with the user and a termination keyword has been detected from the voice, the dialog determination unit determines that the dialog has been terminated.",
"3. A voice dialog method performed by a voice dialog device, comprising: a sight line detecting step of detecting a sight line of a user; a state determining step of determining a state of the user; a voice processing step of obtaining voice pronounced by the user and a result of recognizing the voice; a dialog determining step of determining whether or not the voice dialog device has a dialog with the user; and an answer generating step of generating an answer, based on a result of recognizing the voice, wherein, the dialog determining step includes determining whether or not the user has started the dialog based on both the sight line of the user and the obtained voice by: when state of the user determined by the state determining step is driving a vehicle, the sight line of the user detected by the sight line detecting step is in a vehicle forward direction, and a start keyword has been detected from the voice by the voice processing step, the dialog determining step determines that the user has started a dialog, when the state of the user determined by the state determining step is driving a vehicle and either the sight line of the user detected by the sight line detecting step is not in the vehicle forward direction or the start keyword has not been detected from the voice by the voice processing step, the dialog determining step determines that the user has not started a dialog, when the state of the user determined by the state determining step is not driving a vehicle, the sight line of the user detected by the sight line detecting step is in a direction toward the voice dialogue device, and a start keyword has been detected from the voice by the voice processing step, the dialog determining step determines that the user has started a dialog, and when the state of the user determined by the state determining step is not driving a vehicle and either the sight line of the user detected by the sight line detecting step is not in the direction toward the voice dialogue device or the start keyword has not been detected from the voice, the start keyword has not been detected from the voice by the voice processing step, the dialog determining step determines that the user has not started a dialog.",
"4. A non-transitory computer readable storing medium recording a computer program for causing a computer to perform the voice dialog method according to claim 3."
],
"cpc": [
"G10L 15/22",
"G06F 2203/0381",
"G06F 3/013",
"G06F 3/0304",
"G06F 3/167",
"G06K 9/00255",
"G06K 9/00281",
"G06K 9/00604",
"G06K 9/0061",
"G06V 40/166",
"G06V 40/171",
"G06V 40/19",
"G06V 40/193",
"G10L 15/02",
"G10L 15/08",
"G10L 15/24",
"G10L 2015/223",
"G10L 2015/227",
"G10L 25/78"
],
"assignees": [
"TOYOTA MOTOR CO LTD"
],
"filing_date": "2017-05-18",
"publication_date": "2019-08-27",
"grant_date": "2019-08-27",
"priority_date": "2016-05-27",
"application_number": "US-201715598504-A",
"family_id": "60418273",
"citations": [
"JP2006272471A",
"JP2007181888A",
"JP2015013351A",
"JPH0883093A",
"US2003154084A1",
"US2011106531A1",
"US2012295708A1",
"US2014350942A1",
"US2015062168A1",
"US2015109191A1",
"US2017162197A1",
"US2017270924A1",
"US6076061A",
"US8854303B1",
"US9418653B2"
]
}
Record 1,056 of 5,000 in Patents full text (MLC-0201). Request the full dataset.