@article{
 title = {Isolated word recognition in the Sigma cognitive architecture},
 type = {article},
 year = {2014},
 identifiers = {[object Object]},
 keywords = {Cognitive architecture,Graphical models,Learning,Sigma,Speech recognition,HMM},
 pages = {1-9},
 volume = {10},
 websites = {http://www.sciencedirect.com/science/article/pii/S2212683X14000644},
 publisher = {Elsevier B.V.},
 id = {9fb5c71d-96b7-395a-bae8-c4c680f5c395},
 created = {2015-12-08T18:29:34.000Z},
 file_attached = {true},
 profile_id = {9e66d949-92d0-3e13-8d8c-2d6d8d76d924},
 group_id = {48a053e8-b494-3bde-aa03-1071d9e56815},
 last_modified = {2015-12-08T18:35:19.000Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Joshi2014},
 abstract = {Abstract Symbolic architectures are effective at complex cognitive reasoning, but typically are incapable of important forms of sub-cognitive processing – such as perception – without distinct modules connected to them via low-bandwidth interfaces. Neural architectures, in contrast, may be quite effective at the latter, but typically struggle with the former. Sigma has been designed to leverage the state-of-the-art hybrid (discrete + continuous) mixed (symbolic + probabilistic) capability of graphical models to provide in a uniform non-modular fashion effective forms of, and integration across, both cognitive and sub-cognitive behavior. Here it is shown that Sigma is not only capable of performing a simple variant of speech recognition via the same knowledge structures and reasoning algorithm used for cognitive processing, but also of leveraging its existing knowledge templates and learning algorithm to acquire automatically most of the structures and parameters needed for this recognition activity. },
 bibtype = {article},
 author = {Joshi, Himanshu and Rosenbloom, Paul S and Ustun, Volkan},
 journal = {Biologically Inspired Cognitive Architectures},
 number = {0}
}

{"_id":"tMPxwaQRLgqgZREfR","bibbaseid":"joshi-rosenbloom-ustun-isolatedwordrecognitioninthesigmacognitivearchitecture-2014","downloads":0,"creationDate":"2016-10-11T17:05:15.354Z","title":"Isolated word recognition in the Sigma cognitive architecture","author_short":["Joshi, H.","Rosenbloom, P., S.","Ustun, V."],"year":2014,"bibtype":"article","biburl":null,"bibdata":{"title":"Isolated word recognition in the Sigma cognitive architecture","type":"article","year":"2014","identifiers":"[object Object]","keywords":"Cognitive architecture,Graphical models,Learning,Sigma,Speech recognition,HMM","pages":"1-9","volume":"10","websites":"http://www.sciencedirect.com/science/article/pii/S2212683X14000644","publisher":"Elsevier B.V.","id":"9fb5c71d-96b7-395a-bae8-c4c680f5c395","created":"2015-12-08T18:29:34.000Z","file_attached":"true","profile_id":"9e66d949-92d0-3e13-8d8c-2d6d8d76d924","group_id":"48a053e8-b494-3bde-aa03-1071d9e56815","last_modified":"2015-12-08T18:35:19.000Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Joshi2014","abstract":"Abstract Symbolic architectures are effective at complex cognitive reasoning, but typically are incapable of important forms of sub-cognitive processing – such as perception – without distinct modules connected to them via low-bandwidth interfaces. Neural architectures, in contrast, may be quite effective at the latter, but typically struggle with the former. Sigma has been designed to leverage the state-of-the-art hybrid (discrete + continuous) mixed (symbolic + probabilistic) capability of graphical models to provide in a uniform non-modular fashion effective forms of, and integration across, both cognitive and sub-cognitive behavior. Here it is shown that Sigma is not only capable of performing a simple variant of speech recognition via the same knowledge structures and reasoning algorithm used for cognitive processing, but also of leveraging its existing knowledge templates and learning algorithm to acquire automatically most of the structures and parameters needed for this recognition activity. ","bibtype":"article","author":"Joshi, Himanshu and Rosenbloom, Paul S and Ustun, Volkan","journal":"Biologically Inspired Cognitive Architectures","number":"0","bibtex":"@article{\n title = {Isolated word recognition in the Sigma cognitive architecture},\n type = {article},\n year = {2014},\n identifiers = {[object Object]},\n keywords = {Cognitive architecture,Graphical models,Learning,Sigma,Speech recognition,HMM},\n pages = {1-9},\n volume = {10},\n websites = {http://www.sciencedirect.com/science/article/pii/S2212683X14000644},\n publisher = {Elsevier B.V.},\n id = {9fb5c71d-96b7-395a-bae8-c4c680f5c395},\n created = {2015-12-08T18:29:34.000Z},\n file_attached = {true},\n profile_id = {9e66d949-92d0-3e13-8d8c-2d6d8d76d924},\n group_id = {48a053e8-b494-3bde-aa03-1071d9e56815},\n last_modified = {2015-12-08T18:35:19.000Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Joshi2014},\n abstract = {Abstract Symbolic architectures are effective at complex cognitive reasoning, but typically are incapable of important forms of sub-cognitive processing – such as perception – without distinct modules connected to them via low-bandwidth interfaces. Neural architectures, in contrast, may be quite effective at the latter, but typically struggle with the former. Sigma has been designed to leverage the state-of-the-art hybrid (discrete + continuous) mixed (symbolic + probabilistic) capability of graphical models to provide in a uniform non-modular fashion effective forms of, and integration across, both cognitive and sub-cognitive behavior. Here it is shown that Sigma is not only capable of performing a simple variant of speech recognition via the same knowledge structures and reasoning algorithm used for cognitive processing, but also of leveraging its existing knowledge templates and learning algorithm to acquire automatically most of the structures and parameters needed for this recognition activity. },\n bibtype = {article},\n author = {Joshi, Himanshu and Rosenbloom, Paul S and Ustun, Volkan},\n journal = {Biologically Inspired Cognitive Architectures},\n number = {0}\n}","author_short":["Joshi, H.","Rosenbloom, P., S.","Ustun, V."],"urls":{"Paper":"http://bibbase.org/service/mendeley/9e66d949-92d0-3e13-8d8c-2d6d8d76d924/file/5fea9762-d486-deff-7ba7-b0f38430bf0a/2014-Isolated_word_recognition_in_the_Sigma_cognitive_architecture.pdf.pdf","Website":"http://www.sciencedirect.com/science/article/pii/S2212683X14000644"},"bibbaseid":"joshi-rosenbloom-ustun-isolatedwordrecognitioninthesigmacognitivearchitecture-2014","role":"author","keyword":["Cognitive architecture","Graphical models","Learning","Sigma","Speech recognition","HMM"],"downloads":0},"search_terms":["isolated","word","recognition","sigma","cognitive","architecture","joshi","rosenbloom","ustun"],"keywords":["cognitive architecture","graphical models","learning","sigma","speech recognition","hmm"],"authorIDs":[]}