US 9,384,188 B1 · Transcription correction using multi-token structures

Abstract

Examples of the present disclosure describe generation of a multi-arc confusion network to improve, for example, an ability to return alternatives to output generated. A confusion network comprising token representations of lexicalized hypotheses and normalized hypotheses is generated. Each arc of the confusion network represents a token of a lexicalized hypothesis or a normalized hypothesis. The confusion network is transformed into a multi-arc confusion network, wherein the transforming comprising realigning at least one token of the confusion network to span multiple arcs of the confusion network. Other examples are also described.

Claims20

Dependent claims

A computer-implemented method comprising:

executing speech recognition on a captured input and generating lexicalized hypotheses from the captured input;
normalizing the lexicalized hypotheses to generate normalized hypotheses for the lexicalized hypotheses, wherein a normalized hypothesis comprising one or more tokens;
generating a confusion network comprising token representations of normalized hypotheses, wherein each arc of the confusion network represents a token of a normalized hypothesis;
and
transforming the generated confusion network into a multi-arc confusion network, wherein the transforming comprising realigning at least one token of the confusion network to span multiples arcs of the confusion network.

2 more elements

Dependencies are inferred from the claim text.

Transcription correction using multi-token structures

Life of this patent

Transcription correction using multi-token structures

Life of this patent

Abstract

Claims20