Method of and system for improving accuracy in a speech recognition system

摘要

A method for transcribing an audio response includes: A. constructing an application including a plurality of queries and a set of expected responses for each query, the set including a plurality of expected responses to each query in a textual form; B. posing each of the queries to a respondent with a querying device; C. receiving an audio response to each query from the respondent; D. performing a speech recognition function on each audio response with an automatic speech recognition device to transcribe each audio response to a textual response to each query; E. recording each audio response with a recording device; and F. comparing, with the automatic speech recognition device, each textual response to the set of expected responses for each corresponding query to determine if each textual response corresponds to any of the expected responses in the set of expected responses for the corresponding query.

主权项

1. A speech recognition system comprising:
a querying device for posing at least one query to a respondent; a speech recognition device including a speak recognition application which receives an audio response from said respondent and transcribes said audio response to produce a corresponding text response, wherein the speech recognition device is operative to conduct a speaker-independent speech recognition analysis of said audio response, wherein the speech recognition device comprises means for processing of an acoustic file that is tied to database information resulting from the speech recognition application that audibly plays the acoustic file while presenting a screen to a transcriber for transcription and correction of the database information; a storage device for storing said audio response as it is received by said speech recognition device; and an accuracy determination device operative to compare said text response to a text set of expected responses and to determine whether said text response corresponds to one of said expected responses, wherein said accuracy determination device is operative to determine whether said text response does correspond to one of said expected responses within a predetermined accuracy confidence parameter, and flag said audio response for further review if said response does not correspond to one of said expected responses within the predetermined accuracy confidence parameter.