Fully expanded context-dependent networks for speech recognition
AssigneeAT&T Corp.
InventorsMehryar Mohri, Michael Dennis Riley
Life of this patent
Estimating the term…
Abstract
A large vocabulary speech recognizer including a combined weighted network of transducers reflecting fully expanded context-dependent modeling of pronunciations and language that can be used with a single-pass Viterbi or other coder based on sequences of labels provided by feature analysis of input speech.
Claims20
A method for making a combined weighted speech transducer for a large-vocabulary context-dependent speech recognizer based on signals representing:
- (i) the inverse, C−1, of a context-dependency transducer;
- (ii) a word pronunciation transducer, L;
- and (iii) a language model transducer, G;
- the method comprising the steps of
- generating signals representing transducer C, the inverse of a determinized version of transducer C−1,
- generating signals representing transducer P′, a determinized version of the composition L′BG′, which composition is a composition of disambiguated versions of each of said transducers L and G,
- generating signals representing a transducer P, a minimized version of transducer P′, and
- generating signals representing said combined speech transducer as the composition C B P.
A combined weighted speech transducer for use in a large-vocabulary context-dependent speech recognizer, said transducer stored in a memory system and being based on signals representing:
- (i) the inverse, C−1, of a context-dependency transducer;
- (ii) a word pronunciation transducer, L;
- and (iii) a language model transducer, G;
- said transducer comprising
- signals representing C B P, the composition of transducers C and P, where
- transducer C comprises signals representing the inverse of a determinized version of transducer C−1,
- transfer P comprises signals representing a minimized version of a transducer P′, where transducer P′ is a determinized version of the composition L′BG′, of disambiguated versions of each of said transducers L and G.
A large-vocabulary, context-dependent speech recognizer comprising
- a. a feature extractor for extracting features of input speech signals and applying sequences of one or more labels to said features,
- b. a combined weighted speech transducer for use in a speech recognizer, said transducer being stored in a memory system and being based on signals representing:
- (i) the inverse, C−1, of a context-dependency transducer;
- (ii) a word pronunciation transducer, L;
- and (iii) a language model transducer, G;
- said combined speech transducer comprising signals representing C B P, the composition of transducers C and P, where
- transducer C comprises signals representing the inverse of a determinized version of transducer C−1, and
- transducer P comprises signals representing a minimized version of a transducer P′, where transducer P′ is a determinized version of the composition L′BG′, of disambiguated versions of each of said transducers L and G, and
- c. a decoder for outputting decisions about said input speech signals based on said sequences of labels and said combined speech transducer.
Dependencies are inferred from the claim text.