Representation of orthography in a continuous vector space

Data processing: speech signal processing – linguistics – language – Linguistics

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C704S010000

Reexamination Certificate

active

10242849

ABSTRACT:
An orthographic anchor for each word in a dictionary is created in an orthographic space by mapping the words and a set of letter patterns characteristic of the words into the orthographic space. In one aspect the orthographic anchors are row or column vectors resulting from a decomposition of a matrix of feature vectors created by the mapping. In another aspect, a pronunciation for an input word is modeled based on a set of candidate phoneme strings that have pronunciations close to the input word in the orthographic space.

REFERENCES:
patent: 5040218 (1991-08-01), Vitale et al.
patent: 5268990 (1993-12-01), Cohen et al.
patent: 5301109 (1994-04-01), Landauer et al.
patent: 5333275 (1994-07-01), Wheatley et al.
patent: 5581655 (1996-12-01), Cohen et al.
patent: 5799276 (1998-08-01), Komissarchik et al.
patent: 5828999 (1998-10-01), Bellegarda et al.
patent: 6016471 (2000-01-01), Kuhn et al.
patent: 6029132 (2000-02-01), Kuhn et al.
patent: 6108627 (2000-08-01), Sabourin
patent: 6654740 (2003-11-01), Tokuda et al.
patent: 6684187 (2004-01-01), Conkie
patent: 6778952 (2004-08-01), Bellegarda
patent: 6778962 (2004-08-01), Kasai et al.
patent: 6810379 (2004-10-01), Vermeulen et al.
patent: 6847966 (2005-01-01), Sommer et al.
patent: 6879957 (2005-04-01), Pechter et al.
patent: 6912499 (2005-06-01), Sabourin et al.
patent: 2002/0046025 (2002-04-01), Hain
patent: 2002/0077817 (2002-06-01), Atal
patent: 2005/0196733 (2005-09-01), Budra et al.
Gotoh, et al. “Document space models using latent semantic analysis,” Proc. 5th EuroSpeech, Rhodes, Greece, pp. 1443-1448, Sep. 1997.
Bellegarda et al. “A novel word clustering algoithm based on latent semantic analysis,” IEEE ICASSP-96, Atlanta, GA, May 7-10, 1996, vol. 1, pp. 172-175.
Bellegarda et al. “Large vocabulary speech recognition with multispan statistical language models,” IEEE Transactions on Speech and Audio Processing, vol. 8, Issue 1, Jan. 2000, pp. 76-84.
Schutze, H. “Dimensions of meaning,” Proceedings Supercomputing '92, Nov. 16-20, 1992, pp. 787-796.
Yoon, K., C. Brew, and M. Beckman, “Letter-to-Sound Rules for Korean,” IEEE Workshop on Speech Synthesis, Sep. 2002.
Bellegarda, Jerome R., “Exploiting Latent Semantic Information in Statistical Language Modeling,” Proceedings of the IEEE, Aug. 2000, pp. 1-18.
Vingron, Martin, “Near-Optimal Sequence Alignment,”Curr. Op. Struct. Biology, vol. 6, No. 3, Jun. 1996, 20 pp.
Stefan Werner and Eric Keller, “Prosodic Aspects of Speech”, 1994, Fundamentals of Speech Synthesis and Speech Recognition: Basic Concepts, State of the Art, and Future Challenges, pp. 23-40, Chichester: John Wiley.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Representation of orthography in a continuous vector space does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Representation of orthography in a continuous vector space, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Representation of orthography in a continuous vector space will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-3933283

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.