Estimating an upper bound for the error rate for speech recognition using entropy

AEU-Archiv fur Elektronik und Ubertragungstechnik

Volumn 53, Issue 4, 1999, Pages 205-214

  Höge, Harald ^a  

^a SIEMENS AG   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; INFORMATION THEORY; MATHEMATICAL MODELS; PROBABILITY; SPEECH ANALYSIS;

CONDITIONAL ENTROPY; PHONEME ERROR RATES;

SPEECH RECOGNITION;

EID: 0343168077     PISSN: 00011096     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (13)

1. Schukat-Talamazzini, E.G.: Automatische Spracherkennung - Grundlagen, statistische Modelle und effiziente Algorithmen. Friedr. Vieweg & Sohn Verlagsgesellschaft mbH, 1995.
2. Brown, P.: The Acoustic Modeling Problem in Automatic Speech Recognition. Carnegie Mellon University, USA Pittsburgh, PA. 1987.
3. Ney, H.: "Personal note", 1994.
4. Gallager, R.: Information Theory and Reliable Communication. John Wiley & Sons, 1968.
5. Doddington, G.: Phonetically Sensitive Discriminants for Improved Speech Recognition. Int. Conf. on Acoustics, Speech and Signal Processing, Glasgow 1989, 556-559.
6. Brown P. F. et al.: An Estimate of an Upper Bound for the Entropy of English. Computer Linguistics 18 (1992), 31-40.
7. Kühnen, B.; Nolan, F.: The Origin of Coarticulation. To appear in: Hardcastle, W.J.; Hewlett, N.: Coarticulation: Theoretical and Empirical Perspectives', Cambridge CUP.
8. Heid, S.: Phonetische Variation - Untersuchung anhand des Phondat II Corpus. Thesis in preparation, LMU Munic 1999.
9. Hauenstein, A.; Marschall, E.: Methods for Improved Recognition over Telephone Lines. Int. Conf. on Acoustics, Speech and Signal Processing, Detroit 1995, 425-428.
10. Draxler, C.; Van den Heuvel, H.; Tropf, H.: SpeechDat Experiences in Creating Large Multilingual Speech Databases for Teleservices. Proc. First International Conference on Language Resources & Evaluation, Granada, Spain, May 1998, 361-366.
11. Junkawitsch, J.; Höge, H.: Keyword Verification Considering the Correlation of Succeeding Feature Vectors. Int. Conf. on Acoustics, Speech and Signal Processing, Seattle 1998, 221-224.
12. Duda, H.; Hart, P.: Pattern Classification and Scene. Analysis, John Wiley & Sons, 1973.
13. Bahl, L.; Brown, P.; De Souza, P.; Mercer, R.: Maximal Mutual Information Estimation of Hidden Markov Model Parameters for Speech Recognition. Proc. Int. Conf. on Acoustics, Speech and Signal Processing, Tokyo 1986, 49-52.