System and method of providing an automated data-collection in spoken dialog systems
First Claim
1. A method for gathering data for use in a spoken dialog system having a domain, the method comprising:
- training an automatic speech recognition (ASR) module, spoken language understanding (SLU) module and dialog management (DM) module using task-independent call-types of a previous application;
presenting an initial prompt to a user;
recognizing a received user utterance using the ASR module;
classifying the recognized user utterance using the SLU module;
if the recognized user utterance is understood or classifiable with a confidence more than an acceptance threshold, then acting according to a call-type associated with the classification;
if the recognized user utterance is not understood or classifiable to a predetermined threshold, then re-prompting the user; and
if the recognized user utterance is not classifiable to a predetermined rejection threshold, then transferring the user to a human, wherein the received and classified user utterance is used for training the spoken dialog system.
4 Assignments
0 Petitions
Accused Products
Abstract
The invention relates to a system and method for gathering data for use in a spoken dialog system. An aspect of the invention is generally referred to as an automated hidden human that performs data collection automatically at the beginning of a conversation with a user in a spoken dialog system. The method comprises presenting an initial prompt to a user, recognizing a received user utterance using an automatic speech recognition engine and classifying the recognized user utterance using a spoken language understanding module. If the recognized user utterance is not understood or classifiable to a predetermined acceptance threshold, then the method re-prompts the user. If the recognized user utterance is not classifiable to a predetermined rejection threshold, then the method transfers the user to a human as this may imply a task-specific utterance. The received and classified user utterance is then used for training the spoken dialog system.
73 Citations
29 Claims
-
1. A method for gathering data for use in a spoken dialog system having a domain, the method comprising:
-
training an automatic speech recognition (ASR) module, spoken language understanding (SLU) module and dialog management (DM) module using task-independent call-types of a previous application;
presenting an initial prompt to a user;
recognizing a received user utterance using the ASR module;
classifying the recognized user utterance using the SLU module;
if the recognized user utterance is understood or classifiable with a confidence more than an acceptance threshold, then acting according to a call-type associated with the classification;
if the recognized user utterance is not understood or classifiable to a predetermined threshold, then re-prompting the user; and
if the recognized user utterance is not classifiable to a predetermined rejection threshold, then transferring the user to a human, wherein the received and classified user utterance is used for training the spoken dialog system. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A system for gathering data for use in training a spoken dialog system, the system comprising:
-
means for obtaining task-independent training data;
means for presenting an initial prompt to a user;
means for recognizing a received user utterance using an automatic speech recognition engine;
means for classifying the recognized user utterance using a spoken language understanding module;
means for prompting the user if the recognized user utterance is understood or classifiable with a confidence more than a predetermined acceptance threshold;
means for re-prompting the user if the recognized user utterance is not understood or classifiable to a predetermined acceptance threshold; and
means for transferring the user to a human if the recognized user utterance is not classifiable to a predetermined rejection threshold, wherein the received and classified user utterance is used for training the spoken dialog system. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17)
-
-
18. A system for gathering data for use in training a spoken dialog system, the system comprising:
-
a module configured to determine task-independent training data from a library formed using data from previous applications;
a module configured to present an initial prompt to a user;
a module configured to recognize a received user utterance using an automatic speech recognition engine;
a module configured to classify the recognized user utterance using a spoken language understanding module;
a module configured to re-prompt the user if the recognized user utterance is not understood or classifiable to a predetermined acceptance threshold; and
a module configured to transfer the user to a human if the recognized user utterance is not classifiable to a predetermined rejection threshold, wherein the received and classified user utterance is used for training the spoken dialog system.
-
-
19. A computer-readable medium storing instructions for controlling a computing device to gather data for use in training a spoken dialog system, the instructions comprising the steps:
-
managing a library of training data obtained from previous applications;
presenting an initial prompt to a user;
recognizing a received user utterance using an automatic speech recognition engine;
classifying the recognized user utterance using a spoken language understanding module;
if the recognized user utterance is not understood or classifiable to a predetermined acceptance threshold, then re-prompting the user;
if the recognized user utterance is not classifiable to a predetermined rejection threshold, then transferring the user to a human, wherein the received and classified user utterance is used for training the spoken dialog system. - View Dependent Claims (20, 21, 22, 23, 24)
-
-
25. A method of gathering data for use in training a spoken dialog system, the method comprising:
-
presenting an initial prompt to a user;
recognizing an utterance using an automatic speech recognition (ASR) module;
classifying the utterance using a generic spoken language understanding (SLU) module;
determining whether the recognition and classification meet a threshold;
if the recognition and/or classification does not meet the threshold, then either re-prompting the user or transferring the user to a human agent; and
if the recognition and/or classification does meet the threshold, then routing the call according to a call-type associated with the classification. - View Dependent Claims (26, 27, 28, 29)
-
Specification