Evaluating the Potential Effectiveness of Automatic Document Analysis
- 27 Downloads
This paper documents the motivation, method and results of seven experiments conducted to investigate the properties of automatic document analysis (for the purpose of automatic vocabulary expansion of a personalized language model in a speech dictation system). The results indicated that automatic document analysis of corrected text should improve the accuracy of text dictated in the future, as long as the future text is similar to the analyzed text. None of the manipulations had a measurable effect (either good or bad) when the analyzed text was uncorrected dictation or future text that was not similar to analyzed text. These results were the same for both trained and untrained acoustic models.
Unable to display preview. Download preview PDF.
- Abelson, R. (1995). Statistics as Principled Argument. Hillsdale, NJ: Lawrence Erlbaum.Google Scholar
- Bahl, L.R., Brown, P.F., de Souza, P.V., Mercer, R.L., and Picheny, M.A. (1988). Acoustic Markov models used in the Tangora speech recognition system. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, New York, NY: IEEE, pp. 497–500.Google Scholar
- Bahl, L.R., Das, S.K., de Souza, P.V., Epstein, M., Mercer, R.L., Merialdo, B., Nahamoo, D., Picheny, M.A., and Powell, J. (1991). Automatic phonetic baseform determination. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Toronto, Canada: IEEE, pp. 173–176.Google Scholar
- Das, S.K. and Picheny, M.A. (1996). Issues in practical large vocabulary isolated word recognition: The IBM Tangora system. In C.H. Lee, F.K. Soong, and K.K. Paliwal (Eds.), Automatic Speech and Speaker Recognition: Advanced Topics, Boston, MA: Kluwer Academic Publishers, pp. 457–479.Google Scholar
- Jelinek, F. (1999). Statistical Methods for Speech Recognition. Cambridge, MA: The MIT Press.Google Scholar
- Karat, C.M., Halverson, C., Horn, D., and Karat, J. (1999). Patterns of entry and correction in large vocabulary continuous speech recognition systems. CHI '99 Conference Proceedings, Pittsburgh, PA: Association for Computing Machinery, pp. 568–575.Google Scholar
- Lewis, J.R. (1999). Effect of error correction strategy on speech dictation throughput. Proceedings of the Human Factors and Ergonomics Society, Santa Monica, CA: Human Factors and Ergonomics Society, pp. 457–461.Google Scholar
- Lucassen, J.M. and Mercer, R.L. (1984). An information-theoretic approach to the automatic determination of phonetic baseforms. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, New York, NY: IEEE, pp. 42.5.1–42.5.4.Google Scholar
- Steele, R.G.D. and Torrie, J.H. (1960). Principles and Procedures of Statistics. New York, NY: McGraw-Hill.Google Scholar