About: http://webisa.webdatacommons.org/222385131

Property	Value
http://www.w3.org/1999/02/22-rdf-syntax-ns#type	http://www.w3.org/ns/prov#Entity
http://www.w3.org/ns/prov#value	Training data are partitioned into N acoustic environments using a maximum likelihood technique, which assigns training utterances to one of the N particular acoustic environments, where N is a positive integer, for example two.
http://www.w3.org/ns/prov#wasQuotedFrom	google.com