METHOD AND APPARATUS FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
First Claim
1. A method for extracting a term comprising an at least one word from an audio signal captured in a call center environment, comprising:
- receiving the audio signal captured in the call center environment;
extracting a multiplicity of feature vectors from the audio signal;
creating a phoneme lattice from the multiplicity of feature vectors, the phoneme lattice comprising at least one allophone, the at least one allophone comprising at least two phonemes;
creating a hybrid phoneme-word lattice from the phoneme lattice; and
extracting the word by analyzing the hybrid phoneme-word lattice.
3 Assignments
0 Petitions
Accused Products
Abstract
A method and apparatus combining the advantages of phonetic search such as the rapid implementation and deployment and medium accuracy, with the advantages of speech to text, including providing the full text of the audio and rapid search.
The method and apparatus comprise steps or components for receiving the audio signal captured in the call center environment; extracting a multiplicity of feature vectors from the audio signal; creating a phoneme lattice from the multiplicity of feature vectors, the phoneme lattice comprising one or more allophone, each allophone comprising two or more phonemes; creating a hybrid phoneme-word lattice from the phoneme lattice; and extracting the word by analyzing the hybrid phoneme-word lattice.
55 Citations
19 Claims
-
1. A method for extracting a term comprising an at least one word from an audio signal captured in a call center environment, comprising:
-
receiving the audio signal captured in the call center environment; extracting a multiplicity of feature vectors from the audio signal; creating a phoneme lattice from the multiplicity of feature vectors, the phoneme lattice comprising at least one allophone, the at least one allophone comprising at least two phonemes; creating a hybrid phoneme-word lattice from the phoneme lattice; and extracting the word by analyzing the hybrid phoneme-word lattice. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. An apparatus for extracting a term comprising an at least one word from an audio signal captured in a call center environment, comprising:
-
a capture device for capturing the audio signal in the call center environment; a feature extraction component for extracting a multiplicity of feature vectors from the audio signal; an allophone decoding component for creating a phoneme lattice from the multiplicity of feature vectors, the phoneme lattice comprising at least one allophone, the at least one allophone comprising at least two phonemes; a word decoding component for creating a hybrid phoneme-word lattice from the phoneme lattice; and an analysis component for analyzing the hybrid phoneme-word lattice. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18)
-
-
19. A computer readable storage medium containing a set of instructions for a general purpose computer, the set of instructions comprising:
-
capturing an audio signal in a call center environment extracting a multiplicity of feature vectors from the audio signal; creating a phoneme lattice from the multiplicity of feature vectors, the phoneme lattice comprising at least one allophone, the at least one allophone comprising at least two phonemes; creating a hybrid phoneme-word lattice from the phoneme lattice; and analyzing the hybrid phoneme-word lattice.
-
Specification