Transcription correction using multi-token structures

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 t...

Full description

Saved in:
Bibliographic Details
Main Authors Ozertem Umut, Varadharajan Padma, Raghunathan Karthik, Alphonso Issac, Parthasarathy Sarangarajan, Levit Michael
Format Patent
LanguageEnglish
Published 04.10.2016
Subjects
ACOUSTICS
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online AccessGet full text

Cover

More Information
Summary: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.
Bibliography:Application Number: US201615171149