%Aigaion2 BibTeX export from Idiap Publications %Thursday 21 November 2024 12:37:14 PM @TECHREPORT{dupont-RR-97-14, author = {Dupont, St{\'{e}}phane and Luettin, Juergen}, projects = {Idiap}, title = {Using the Multi-Stream Approach for Continuous Audio-Visual Speech Recognition}, type = {Idiap-RR}, number = {Idiap-RR-14-1997}, year = {1997}, institution = {IDIAP}, abstract = {The Multi-Stream automatic speech recognition approach was investigated in this work as a framework for Audio-Visual data fusion and speech recognition. This method presents many potential advantages for such a task. It particularly allows for synchronous decoding of continuous speech while still allowing for some asynchrony of the visual and acoustic information streams. First, the Multi-Stream formalism is briefly recalled. Then, on top of the Multi-Stream motivations, experiments on the {\sc M2VTS} multimodal database are presented and discussed. To our knowledge, these are the first experiments about multi-speaker continuous Audio-Visual Speech Recognition (AVSR). It is shown that the Multi-Stream approach can yield improved Audio-Visual speech recognition performance when the acoustic signal is corrupted by noise as well as for clean speech.}, pdf = {https://publications.idiap.ch/attachments/reports/1997/rr97-14.pdf}, postscript = {ftp://ftp.idiap.ch/pub/reports/1997/rr97-14.ps.gz}, ipdmembership={vision}, }