%Aigaion2 BibTeX export from Idiap Publications
%Friday 05 December 2025 01:09:43 PM
@ARTICLE{morris-spcom1.bib,
author = {Morris, Andrew and Hagen, Astrid and Glotin, Herv{\'{e}} and Bourlard, Herv{\'{e}}},
projects = {Idiap},
title = {Multi-stream adaptive evidence combination for noise robust ASR},
journal = {Speech Communication},
year = {2001},
publisher = {NORTH-HOLLAND},
crossref = {morris-RR-99-26},
abstract = {In this paper we develop different mathematical models in the framework of the multi-stream paradigm for noise robust ASR, and discuss their close relationship with human speech perception. Largely inspired by Fletcher's "product-of-errors" rule in psychoacoustics, multi-band ASR aims for robustness to data mismatch through the exploitation of spectral redundancy, while making minimum assumptions about noise type. Previous ASR tests have shown that independent sub-band processing can lead to decreased recognition performance with clean speech. We have overcome this problem by considering every combination of data sub-bands as an independent data stream. After introducing the background to multi-band ASR, we show how this "full combination" approach can be formalised, in the context of HMM/ANN based ASR, by introducing a latent variable to specify which data sub-bands in each data frame are free from data mismatch. This enables us to decompose the posterior probability for each phoneme into a reliability weighted integral over all possible positions of clean data. This approach offers great potential for adaptation to rapidly changing and unpredictable noise.},
ipdmembership={speech},
}
crossreferenced publications:
@TECHREPORT{morris-RR-99-26,
author = {Morris, Andrew and Hagen, Astrid and Glotin, Herv{\'{e}} and Bourlard, Herv{\'{e}}},
keywords = {evidence combination, multi-stream processing, noise adaptation, robust ASR},
projects = {Idiap},
title = {Multi-stream adaptive evidence combination for noise robust ASR},
type = {Idiap-RR},
number = {Idiap-RR-26-1999},
year = {1999},
institution = {IDIAP},
abstract = {In this paper we develop different mathematical models in the framework of the multi-stream paradigm for noise robust ASR, and discuss their close relationship with human speech perception. Largely inspired by Fletcher's "product-of-errors" rule in psychoacoustics, multi-band ASR aims for robustness to data mismatch through the exploitation of spectral redundancy, while making minimum assumptions about noise type. Previous ASR tests have shown that independent sub-band processing can lead to decreased recognition performance with clean speech. We have overcome this problem by considering every combination of data sub-bands as an independent data stream. After introducing the background to multi-band ASR, we show how this "full combination" approach can be formalised, in the context of HMM/ANN based ASR, by introducing a latent variable to specify which data sub-bands in each data frame are free from data mismatch. This enables us to decompose the posterior probability for each phoneme into a reliability weighted integral over all possible positions of clean data. This approach offers great potential for adaptation to rapidly changing and unpredictable noise.},
pdf = {https://publications.idiap.ch/attachments/reports/1999/rr99-26.pdf},
postscript = {ftp://ftp.idiap.ch/pub/reports/1999/rr99-26.ps.gz},
ipdmembership={speech},
}