Conversational speech analysis method, and conversational speech analyzer
First Claim
Patent Images
1. A conversational speech analyzing system, comprising:
- a data capturing unit configured to capture data of a conversation or meeting;
a motion sensor configured to capture motion information of a person involved in the conversation or meeting; and
a computer, including;
a frame detection unit configured to detect frames based on the captured data, a frame being a time segment of the conversation or meeting, and wherein the frame detection unit is configured to detect a first set of frames of data associated with a first person by using a second set of frames of data associated with a second person,a feature extraction unit configured to extract feature information from the sensor information of the first person in the first set of frames,a calculation unit configured to calculate a state of the first person in the conversation or meeting, including an interest level of the first person in the meeting, and to calculate a change of the state of the first person, including a change in interest level of the first person in the meeting, anda display unit configured to display at least one of;
the state of the first person involved in the conversation or meeting, including a symbol of the first person, the symbol including a circle whose radius corresponds to a quantity of comments made by the first person in the conversation or meeting found to be useful or interesting by other participants,a plurality of time segments forming a time series, each time segment represented by a symbol including a rectangle whose shade or color corresponds to an aggregate of interest levels of persons involved in the conversation or meeting, andchanges of the state of the first person shown in chronological order, including a graph that corresponds to the change over time in an interest level of the first person in the conversation or meeting.
0 Assignments
0 Petitions
Accused Products
Abstract
The invention provides a conversational speech analyzer which analyzes whether utterances in a meeting are of interest or concern. Frames are calculated using sound signals obtained from a microphone and a sensor, sensor signals are cut out for each frame, and by calculating the correlation between sensor signals for each frame, an interest level which represents the concern of an audience regarding utterances is calculated, and the meeting is analyzed.
-
Citations
19 Claims
-
1. A conversational speech analyzing system, comprising:
-
a data capturing unit configured to capture data of a conversation or meeting; a motion sensor configured to capture motion information of a person involved in the conversation or meeting; and a computer, including; a frame detection unit configured to detect frames based on the captured data, a frame being a time segment of the conversation or meeting, and wherein the frame detection unit is configured to detect a first set of frames of data associated with a first person by using a second set of frames of data associated with a second person, a feature extraction unit configured to extract feature information from the sensor information of the first person in the first set of frames, a calculation unit configured to calculate a state of the first person in the conversation or meeting, including an interest level of the first person in the meeting, and to calculate a change of the state of the first person, including a change in interest level of the first person in the meeting, and a display unit configured to display at least one of; the state of the first person involved in the conversation or meeting, including a symbol of the first person, the symbol including a circle whose radius corresponds to a quantity of comments made by the first person in the conversation or meeting found to be useful or interesting by other participants, a plurality of time segments forming a time series, each time segment represented by a symbol including a rectangle whose shade or color corresponds to an aggregate of interest levels of persons involved in the conversation or meeting, and changes of the state of the first person shown in chronological order, including a graph that corresponds to the change over time in an interest level of the first person in the conversation or meeting. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A conversational speech analyzing system, comprising:
-
a data capturing unit configured to capture data of a conversation or meeting; a motion sensor configured to capture motion information of a person involved in the conversation or meeting; and a computer, including; a frame detection unit configured to detect frames based on the captured data, a frame being a time segment of the conversation or meeting, and wherein the frame detection unit is configured to detect a first set of frames of data associated with a first person by using a second set of frames of data associated with a second person, a feature extraction unit configured to extract, for the first person involved in the conversation or meeting, feature information from the sensor information in the first set of frames, an interest level extraction unit configured to extract an interest level, within a particular frame in the conversation, for the first person involved in the conversation or meeting, and a display unit configured to display at least one of; a symbol of the first person involved in the conversation or meeting, the symbol including a circle whose radius corresponds to a quantity of comments made by the first person in the conversation or meeting found to be useful or interesting by other participants, a plurality of time segments forming a time series, each time segment represented by a symbol including a rectangle whose shade or color corresponds to an aggregate of interest levels of persons involved in the conversation or meeting, and a graph that corresponds to the change over time in an interest level of the first person in the conversation or meeting. - View Dependent Claims (9, 10, 11, 12)
-
-
13. A conversational speech analyzing system, comprising:
-
a data capturing means for capturing data of a meeting; a motion sensing means for capturing motion information of persons involved in the meeting; and a computing means, including; a frame detection means for detecting frames based on the captured data, a frame being a time segment of the meeting, and wherein the frame detection means detects a first set of frames of data associated with a first person by using a second set of frames of data associated with a second person, a feature extraction means for extracting feature information from the sensor information of the first person in the first set of frames, a calculation means for calculating a state of the first person in the conversation or meeting, including an interest level of the first person in the meeting, and for calculating a change of the state of the first person, including a change in interest level of the first person in the meeting, and a display means for displaying at least one of; the state of the first person involved in the conversation or meeting, including a symbol of the first person, the symbol including a circle whose radius corresponds to a quantity of comments made by the first person in the conversation or meeting found to be useful or interesting by other participants, a plurality of time segments forming a time series, each time segment represented by a symbol including a rectangle whose shade or color corresponds to an aggregate of interest levels of persons involved in the conversation or meeting, and changes of the state of the first person shown in chronological order, including a graph that corresponds to the change over time in an interest level of the first person in the conversation or meeting. - View Dependent Claims (14, 15, 16, 17, 18, 19)
-
Specification
-
- Resources
Litigation Campaign Assessment
Thank you for your request. You will receive a custom alert email when the Litigation Campaign Assessment is available.
×
-
Current AssigneeHitachi, Ltd.
-
Original AssigneeHitachi, Ltd.
-
InventorsSato, Nobuo, Obuchi, Yasunari
-
Primary Examiner(s)Vo, Huyen X.
-
Application NumberUS13/232,125Publication NumberTime in Patent Office580 DaysField of Search704/245, 704/243, 704/244, 704/250, 704/270, 704/272, 704/9, 704/251, 704/255, 704/257US Class Current704/270CPC Class CodesG10L 17/26 Recognition of special voic...G10L 25/78 Detection of presence or ab...
