System and method for classification of voice signals

• US 7,389,230 B1
• Filed: 04/22/2003
• Issued: 06/17/2008
• Est. Priority Date: 04/22/2003
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Nelken, Israel
• Primary Examiner(s): Hudspeth; David
• Assistant Examiner(s): Sked; Matthew J
• Application Number:
  US10/421,356
• Time in Patent Office: 1,883 Days
• Field of Search: None
• US Class Current: 704/255
• CPC Class Codes: G10L 15/14 using statistical models, e.g. Hidden Markov Models [HMMs] G10L15/18 takes precedence
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning

Abstract

A system and method for classifying a voice signal to one of a set of predefined categories, based upon a statistical analysis of features extracted from the voice signal. The system includes an acoustic processor and a classifier. The acoustic processor extracts features that are characteristic of the voice signal and generates feature vectors using the extracted spectral features. The classifier uses the feature vectors to compute the probability that the voice signal belongs to each of the predefined categories and classifies the voice signal to a predefined category that is associated with the highest probability.

Claims

1. A system for classifying a voice signal, comprising:

an acoustic processor configured to receive the voice signal, to generate feature vectors that characterize the voice signal, and to assign an integer label to each generated feature vector; and

a classifier coupled to the acoustic processor to classify the voice signal to one of a set of predefined categories based upon a statistical analysis of the integer labels associated with the feature vectors, wherein the classifier uses one or more probability suffix trees (PSTs) to compute a probability of occurrence of the integer labels being classified in the set of predefined categories.

2. The system of claim 1, wherein the system further comprises a framer configured to segment the voice signal into frames.

3. The system of claim 1, wherein the acoustic processor comprises a feature extractor configured to extract statistical features characteristic of the voice signal.

4. The system of claim 1, further comprising a memory for storing identities of agents, each agent being associated with one of the set of predefined categories.

5. The system of claim 1, wherein the classifier computes a probability that the voice signal belongs to each of the set of predefined categories using the integer labels assigned to the feature vectors.

6. The system of claim 5, wherein the classifier classifies the voice signal to the predefined category in the set of predefined categories that is associated with the highest probability.

7. The system of claim 1, wherein the classifier routes a caller associated with the voice signal to an agent associated with the predefined category.

8. A method for classifying a voice signal, comprising the steps of:

generating a digital discrete-time representation of the voice signal;

generating feature vectors from the digital discrete-time representation;

assigning an integer label to each feature vector; and

classifying the voice signal to one of a set of predefined categories based upon a statistical analysis of the integer labels, wherein the classifying step uses one or more probability suffix trees (PSTs) to compute a probability of occurrence of the integer labels being classified in the set of predefined categories.

9. The method of claim 8, further comprising the step of segmenting the voice signal into frames.

10. The method of claim 8, wherein the step of generating feature vectors from the digital discrete-time representation further comprises the step of extracting statistical features that characterize the voice signal.

11. The method of claim 8, wherein the step of classifying the voice signal further comprises the step of computing a probability that the voice signal belongs to each of the set of predefined categories using the integer labels.

12. The method of claim 11, wherein the step of classifying the voice signal further comprises classifying the voice signal to the predefined category in the set of predefined categories that is associated with the highest probability.

13. The method of claim 8, further comprising the steps of:

associating an agent with each predefined category; and

routing a caller associated with the voice signal to the agent associated with the one of the set of predefined categories.

14. A method for classifying a voice signal, comprising the steps of:

generating a digital discrete-time representation of the voice signal;

segmenting the digital discrete-time representation of the voice signal into frames;

extracting statistical features from each frame that characterize the voice signal;

generating a feature vector from each frame using the extracted statistical features;

assigning an integer label to each feature vector; and

classifying the voice signal to one of a set of predefined categories based upon a statistical analysis of the integer labels, wherein the classifying step uses one or more probability suffix trees (PSTs) to compute a probability of occurrence of the integer labels being classified in the set of predefined categories.

15. A system for classifying a voice signal, comprising:

means for generating a digital discrete-time representation of the voice signal;

means for segmenting the digital discrete-time representation of the voice signal into frames;

means for extracting statistical features from each frame that characterize the voice signal;

means for generating a feature vector from each frame using the extracted statistical features;

means for associating an integer label to each feature vector; and

means for classifying the voice signal to one of a set of predefined categories based upon a statistical analysis of the integer labels, wherein the means for classifying uses one or more probability suffix trees (PSTs) to compute a probability of occurrence of the integer labels being classified in the set of predefined categories.