Evaluation of perceptual delay impact on conversation in teleconferencing system
First Claim
1. A method of evaluating perceptual delay impact on a teleconferencing conversation, comprising:
- detecting a conversational event between a first participant and a second participant, the conversational event including a plurality of speech segments;
in response to the conversational event being detected, obtaining at least one conversational parameter for the first and second participants, the at least one conversational parameter indicating a relationship between the plurality of speech segments in the conversational event; and
determining a quality of the conversation according to a model based on the at least one conversational parameter, the model characterizing the quality with the at least one conversational parameter, wherein the obtaining the at least one conversational parameter comprises;
determining a type of the conversational event, the type being selected from a group consisting of;
a collision type where a first speech segment from the first participant is at least partially overlapped with a second speech segment from the second participant, anda non-collision type where adjacent speech segments of the plurality of speech segments are separated from one another; and
obtaining the at least one conversational parameter based on the determined type of the conversational event, comprising, in response to determining that the conversational event is of the non-collision type, obtaining a first conversational parameter related to a waiting interval between a third speech segment initiated from the first participant and a next fourth speech segment received by the first participant from the second participant.
1 Assignment
0 Petitions
Accused Products
Abstract
Example embodiments disclosed herein relate to an evaluation of perceptual delay impact on a conversation. A method of evaluating perceptual delay impact on a conversation is disclosed. The method includes detecting a conversational event between a first participant and a second participant, the conversational event including a plurality of speech segments; in response to the conversational event being detected, obtaining at least one conversational parameter for the first and second participants, the at least one conversational parameter indicating a relationship between the plurality of speech segments in the conversational event; and determining a quality of the conversation according to a model based on the at least one conversational parameter, the model characterizing the quality with the at least one conversational parameter. A method of obtaining a model for evaluating perceptual delay impact on a conversation is also disclosed. Corresponding systems and computer program products are also disclosed.
24 Citations
15 Claims
-
1. A method of evaluating perceptual delay impact on a teleconferencing conversation, comprising:
-
detecting a conversational event between a first participant and a second participant, the conversational event including a plurality of speech segments; in response to the conversational event being detected, obtaining at least one conversational parameter for the first and second participants, the at least one conversational parameter indicating a relationship between the plurality of speech segments in the conversational event; and determining a quality of the conversation according to a model based on the at least one conversational parameter, the model characterizing the quality with the at least one conversational parameter, wherein the obtaining the at least one conversational parameter comprises; determining a type of the conversational event, the type being selected from a group consisting of; a collision type where a first speech segment from the first participant is at least partially overlapped with a second speech segment from the second participant, and a non-collision type where adjacent speech segments of the plurality of speech segments are separated from one another; and obtaining the at least one conversational parameter based on the determined type of the conversational event, comprising, in response to determining that the conversational event is of the non-collision type, obtaining a first conversational parameter related to a waiting interval between a third speech segment initiated from the first participant and a next fourth speech segment received by the first participant from the second participant. - View Dependent Claims (2, 3, 4, 15)
-
-
5. A method of obtaining a model for evaluating perceptual delay impact on a teleconferencing conversation based on at least one conversational parameter, the at least one conversational parameter indicating a relationship between a plurality of speech segments in a conversational event between a first participant and a second participant of the conversation, the method comprising:
-
selecting a parametric function as the model, the parametric function being defined by the at least one conversational parameter and a coefficient as inputs, and a quality value as an output; receiving a first conversational parameter of a first conversation; receiving a first reference value indicating a user'"'"'s degree of satisfaction on the delay of the first conversation; and determining the coefficient by reducing a difference between the quality value and the first reference value below a threshold difference, wherein the first conversation includes at least one conversational event of a non-collision type where adjacent speech segments of the plurality of speech segments are separated from one another, and the first conversational parameter is related to a waiting interval between a speech segment initiated from the first participant and a next speech segment received by the first participant from the second participant. - View Dependent Claims (6, 7)
-
-
8. A system for evaluating perceptual delay impact on a teleconferencing conversation, comprising:
-
an event detector configured to detect a conversational event between a first participant and a second participant, the conversational event including a plurality of speech segments; a parameter obtainer configured to obtain, in response to the conversational event being detected, at least one conversational parameter for the first and second participants, the at least one conversational parameter indicating a relationship between the plurality of speech segments in the conversational event; and a quality determiner configured to determine a quality of the conversation according to a model based on the at least one conversational parameter, the model characterizing the quality with the at least one conversational parameter, wherein the parameter obtainer further comprises a type determiner configured to determine a type of the conversational event, the type being selected from a group consisting of; a collision type where a first speech segment from the first participant is at least partially overlapped with a second speech segment from the second participant, and a non-collision type where adjacent speech segments of the plurality of speech segments are separated from one another, and wherein the parameter obtainer is further configured to obtain the at least one conversational parameter based on the determined type of the conversational event, wherein the parameter obtainer further comprises a waiting interval parameter obtainer configured to, in response to the type determiner determining that the conversational event is of the non-collision type, obtain a first conversational parameter related to a waiting interval between a third speech segment initiated from the first participant and a next fourth speech segment received by the first participant from the second participant. - View Dependent Claims (9, 10, 11)
-
-
12. A system for obtaining a model for evaluating perceptual delay impact on a teleconferencing conversation based on at least one conversational parameter, the at least one conversational parameter indicating a relationship between a plurality of speech segments in a conversational event between a first participant and a second participant of the conversation, the system comprising:
-
a parametric function selector configured to select a parametric function as the model, the parametric function being defined by the at least one conversational parameter and a coefficient as inputs, and a quality value as an output; a parameter receiver configured to receiving a first conversational parameter of a first conversation; a reference receiver configured to receive a first reference value indicating a user'"'"'s degree of satisfaction on the delay of the first conversation; and a coefficient determiner configured to determine the coefficient by reducing a difference between the quality value and the first reference value below a threshold difference, wherein the first conversation includes at least one conversational event of a non-collision type where adjacent speech segments of the plurality of speech segments are separated from one another, and the first conversational parameter is related to a waiting interval between a speech segment initiated from the first participant and a next speech segment received by the first participant from the second participant. - View Dependent Claims (13, 14)
-
Specification