Speech model refinement with transcription error detection

Details Speech model refinement with transcription error detection Speech model refinement with transcription error detection

2007-04-24

2010-12-28

McFadden, Susan (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

Reexamination Certificate

active

07860716

ABSTRACT:
Reliable transcription error-checking algorithm that uses a word confidence score and a word duration probability to detect transcription errors for improved results through the automatic detection of transcription errors in a corpus. The transcription error-checking algorithm is combined model training so as to use a current model to detect transcription errors, remove utterances which contain incorrect transcription (or manually fix the found errors), and retrain the model. This process can be repeated for several iterations to obtain an improved speech recognition model. The speech model is employed to achieve speech-transcription alignment to obtain a word boundary. Speech recognizer is then utilized to generate a word-lattice. Using the word boundary and word lattice, error detection is computed using a word confidence score and a word duration probability.

REFERENCES:
patent: 6122613 (2000-09-01), Baker
patent: 6912498 (2005-06-01), Stevens et al.
patent: 7003463 (2006-02-01), Maes et al.
patent: 7031918 (2006-04-01), Hwang
patent: 7072836 (2006-07-01), Shao
patent: 7165031 (2007-01-01), Rees
patent: 7519536 (2009-04-01), Maes et al.
patent: 2005/0033574 (2005-02-01), Kim et al.
patent: 2005/0049868 (2005-03-01), Busayapongchai
patent: 2006/0122834 (2006-06-01), Bennett
Evermann, et al., “Posterior Probability Decoding, Confidence Estimation and System Combination” http://www.itl.nist.gov/iaui/894.01/publications/tw00/pdf/cp230.pdf.
Riccardi, et al., “Active and Unsupervised Learning for Automatic Speech Recognition” http://citeseer.ist.psu.edu/cache/papers/cs/32892/http:zSzzSzwww.research.att.comzSz ˜dturzSzpubszSzES-03-AL-UL.pdf/riccardi03active.pdf.
Soong, et al., “Generalized Word Posterior Probability (Gwpp) for Measuring Reliability of Recognized Words” http://www.geocities.com/wklo/doc/SoongSWIM2004.pdf.
Wessel, et al., “Confidence Measures for Large Vocabulary Continuous Speech D Recognition”, Date: Mar. 2001, vol: 9, No. 3, http://www-i6.informatik.rwth-aachen.de/PostScript/InterneArbeiten/Wessel—ConfMeasForLVCSR—IEEESAP2001—March2001.pdf.

Affiliated with

Also associated with

Rating

Speech model refinement with transcription error detection does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speech model refinement with transcription error detection, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech model refinement with transcription error detection will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4222322