000082660 001__ 82660
000082660 005__ 20180317093230.0
000082660 037__ $$aARTICLE
000082660 245__ $$aMulti-stream adaptive evidence combination for noise robust ASR
000082660 269__ $$a2001
000082660 260__ $$bNORTH-HOLLAND$$c2001
000082660 336__ $$aJournal Articles
000082660 520__ $$aIn this paper we develop different mathematical models in the framework of the multi-stream paradigm for noise robust ASR, and discuss their close relationship with human speech perception. Largely inspired by Fletcher's "product-of-errors" rule in psychoacoustics, multi-band ASR aims for robustness to data mismatch through the exploitation of spectral redundancy, while making minimum assumptions about noise type. Previous ASR tests have shown that independent sub-band processing can lead to decreased recognition performance with clean speech. We have overcome this problem by considering every combination of data sub-bands as an independent data stream. After introducing the background to multi-band ASR, we show how this "full combination" approach can be formalised, in the context of HMM/ANN based ASR, by introducing a latent variable to specify which data sub-bands in each data frame are free from data mismatch. This enables us to decompose the posterior probability for each phoneme into a reliability weighted integral over all possible positions of clean data. This approach offers great potential for adaptation to rapidly changing and unpredictable noise.
000082660 6531_ $$amulti-stream processing
000082660 6531_ $$aevidence combination
000082660 6531_ $$anoise adaptation
000082660 6531_ $$arobust ASR
000082660 6531_ $$aspeech
000082660 700__ $$aMorris, Andrew
000082660 700__ $$aHagen, Astrid
000082660 700__ $$aGlotin, Hervé
000082660 700__ $$0243348$$aBourlard, Hervé$$g117014
000082660 773__ $$tSpeech Communication
000082660 8564_ $$uhttp://publications.idiap.ch/index.php/publications/showcite/morris-RR-99-26$$zRelated documents
000082660 909CO $$ooai:infoscience.tind.io:82660$$particle$$pSTI
000082660 909C0 $$0252189$$pLIDIAP$$xU10381
000082660 937__ $$aEPFL-ARTICLE-82660
000082660 970__ $$amorris-spcom1.bib/LIDIAP
000082660 973__ $$aEPFL$$sPUBLISHED
000082660 980__ $$aARTICLE