CONF stephenson00c/IDIAP Automatic Speech Recognition using Dynamic Bayesian Networks with both Acoustic and Articulatory Variables Stephenson, Todd Andrew Bourlard, Hervé Bengio, Samy Morris, Andrew EXTERNAL https://publications.idiap.ch/attachments/papers/2000/todd-icslp2000.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/stephenson00b Related documents 6th International Conference on Spoken Language Processing: ICSLP~2000 (Interspeech~2000) 2000 Beijing October 2000 II:951-954 IDIAP-RR 00-19 Current technology for automatic speech recognition (ASR) uses hidden Markov models (HMMs) that recognize spoken speech using the acoustic signal. However, no use is made of the causes of the acoustic signal: the articulators. We present here a dynamic Bayesian network (DBN) model that utilizes an additional variable for representing the state of the articulators. A particular strength of the system is that, while it uses measured articulatory data during its training, it does not need to know these values during recognition. As Bayesian networks are not used often in the speech community, we give an introduction to them. After describing how they can be used in ASR, we present a system to do isolated word recognition using articulatory information. Recognition results are given, showing that a system with both acoustics and inferred articulatory positions performs better than a system with only acoustics. REPORT stephenson00b/IDIAP Automatic Speech Recognition using Dynamic Bayesian Networks with both Acoustic and Articulatory Variables Stephenson, Todd Andrew Bourlard, Hervé Bengio, Samy Morris, Andrew EXTERNAL https://publications.idiap.ch/attachments/reports/2000/rr00-19.pdf PUBLIC Idiap-RR-19-2000 2000 IDIAP In ``6th International Conference on Spoken Language Processing: ICSLP~2000 (Interspeech~2000)'', 2000 Current technology for automatic speech recognition (ASR) uses hidden Markov models (HMMs) that recognize spoken speech using the acoustic signal. However, no use is made of the causes of the acoustic signal: the articulators. We present here a dynamic Bayesian network (DBN) model that utilizes an additional variable for representing the state of the articulators. A particular strength of the system is that, while it uses measured articulatory data during its training, it does not need to know these values during recognition. As Bayesian networks are not used often in the speech community, we give an introduction to them. After describing how they can be used in ASR, we present a system to do isolated word recognition using articulatory information. Recognition results are given, showing that a system with both acoustics and inferred articulatory positions performs better than a system with only acoustics.