XTranscript

Home | Convert

File:		A single document or a zip-file containing documents to convert.
Config:	Basic (utterance detection and tokenisation) Conversation Analysis notation (Jefferson system) Corpus of Academic Spoken English (CASE)	Find more details on the home page.
Semi-Lexical forms: laugh hah laugh heh laugh hih laugh hoh laugh ha laugh ho laugh hee laugh h laugh haha laugh hehe laugh hoho laugh ha-ha laugh he-he laugh ho-ho filled-pause ehm filled-pause er filled-pause erm filled-pause uh filled-pause uhm filled-pause um filled-pause unh backchannel hm backchannel huh backchannel m backchannel mh backchannel mhm backchannel uh-huh backchannel uh-uh backchannel uhuh backchannel hunm backchannel nu-huh backchannel nuhuh backchannel uh-hum backchannel uhum backchannel hunh backchannel unh-unh backchannel unhunh interjection ah interjection aha interjection ah-ah interjection ahah interjection ugh interjection urgh interjection tsk matched repeated characters
part-of-speech tagging		English only, uses the Stanford CoreNLP tagger. Alternatively, the XML produced by XTranscript should be compatible with other XML aware taggers, such as the CLAWS tagger.