%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 12:35:16 PM

@INPROCEEDINGS{misr06,
         author = {Misra, Hemant and Vepa, Jithendra and Bourlard, Herv{\'{e}}},
       projects = {Idiap},
          month = {9},
          title = {Multi-stream {ASR}: An Oracle Perspective},
      booktitle = {Proceedings of ISCA International Conference on Spoken Language Processing (ICSLP)},
           year = {2006},
        address = {Pittsburgh, U.S.A.},
           note = {IDIAP-RR 2005 62},
       crossref = {misra-rr-05-62},
       abstract = {Multi-stream based automatic speech recognition (ASR) systems outperform their single stream counterparts, specially in case of noisy speech. The main issues in multi-stream systems are: a) Find the feature streams carrying complementary information, and b) Combine the outputs of the classifiers trained on these feature streams. This paper investigates an `oracle' test to address these issues. An interpretation of the oracle test is proposed that can indicate the complimentary of the feature streams used in a multi-stream system. Also, we investigate the statistical nature of the oracle and study the relationship between oracle selection and entropy at the output of the classifiers. In the experiments carried out on two multi-stream systems, approximately 80\\% of the time oracle selected the classifier which had the minimum output entropy. The oracle analysis is supported by results obtained on multi-stream systems using different feature streams and inverse entropy method for weighting.},
            pdf = {https://publications.idiap.ch/attachments/reports/2006/misra_2006_icslp.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2006/misra_2006_icslp.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{misra-rr-05-62,
         author = {Misra, Hemant and Vepa, Jithendra and Bourlard, Herv{\'{e}}},
       projects = {Idiap},
          title = {Multi-stream {ASR}: Oracle Test and Embedded Training},
           type = {Idiap-RR},
         number = {Idiap-RR-62-2005},
           year = {2005},
    institution = {IDIAP},
        address = {Martigny, Switzerland},
           note = {{in Proceedings of ISCA International Conference on Spoken Language Processing (ICSLP,',','),
 2006}},
       abstract = {Multi-stream based automatic speech recognition (ASR) systems outperform their single stream counterparts, especially in the case of noisy speech. However, the main issues in multi-stream systems are to know a) Which streams to be combined, and b) How to combine them. In order to address these issues, we have investigated an `Oracle' test, which can tell us whether two streams are complimentary. Moreover, the Oracle test justifies our previously proposed inverse entropy method for weighting various streams. We have carried out experiments on two multi-stream systems and results indicate that in clean speech around 80\\% of the time Oracle selected the stream which had the minimum entropy. In this paper, we have also presented an embedded iterative training for multi-stream systems. The results of the recognition experiments on Numbers95 database showed that we can improve the performance significantly by multi-stream iterative training, not only for clean speech but also for various noise conditions.},
            pdf = {https://publications.idiap.ch/attachments/reports/2005/rr05-62.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2005/rr05-62.ps.gz},
ipdinar={2005},
ipdmembership={speech},
language={English},
}