{"id":"https://openalex.org/W2103069945","doi":"https://doi.org/10.1109/icassp.2008.4518791","title":"An instantaneous vector representation of delta pitch for speaker-change prediction in conversational dialogue systems","display_name":"An instantaneous vector representation of delta pitch for speaker-change prediction in conversational dialogue systems","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2103069945","doi":"https://doi.org/10.1109/icassp.2008.4518791","mag":"2103069945"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518791","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030859194","display_name":"Kornel Laskowski","orcid":"https://orcid.org/0009-0008-8060-6913"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kornel Laskowski","raw_affiliation_strings":["Centre for Speech Technology, KTH, Stockholm, Sweden","interACT, Carnegie Mellon University, Pittsburgh, PA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology, KTH, Stockholm, Sweden","institution_ids":[]},{"raw_affiliation_string":"interACT, Carnegie Mellon University, Pittsburgh, PA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048337372","display_name":"Jens Edlund","orcid":"https://orcid.org/0000-0001-9327-9482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jens Edlund","raw_affiliation_strings":["Centre for Speech Technology, KTH, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology, KTH, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065281472","display_name":"Mattias Heldner","orcid":"https://orcid.org/0000-0002-0034-0924"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mattias Heldner","raw_affiliation_strings":["Centre for Speech Technology, KTH, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology, KTH, Stockholm, Sweden","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5252,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93828585,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"34","issue":null,"first_page":"5041","last_page":"5044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7604085206985474},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7372320294380188},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6233188509941101},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5952618718147278},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.5418174862861633},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5245775580406189},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.497268944978714},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.4819314479827881},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.44388291239738464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41292959451675415},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07679244875907898}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7604085206985474},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7372320294380188},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6233188509941101},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5952618718147278},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.5418174862861633},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5245775580406189},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.497268944978714},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.4819314479827881},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.44388291239738464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41292959451675415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07679244875907898},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2008.4518791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518791","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.7610","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.7610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~kornel/pubs/laskowskiICASSP2008_published.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.553.7497","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.553.7497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.kth.se/~heldner/papers/laskowskiICASSP2008_published.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.740.8551","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.740.8551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Ekornel/pubs/laskowskiICASSP2008.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W68208136","https://openalex.org/W1499881690","https://openalex.org/W1500409521","https://openalex.org/W1578140299","https://openalex.org/W1975885651","https://openalex.org/W2008986570","https://openalex.org/W2049114856","https://openalex.org/W2118142207","https://openalex.org/W2188508946","https://openalex.org/W4238582696","https://openalex.org/W4251147885","https://openalex.org/W6629661887","https://openalex.org/W6629818233","https://openalex.org/W6634584970"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W2909357361","https://openalex.org/W4387098302","https://openalex.org/W4254851101","https://openalex.org/W4288365855","https://openalex.org/W2948317131"],"abstract_inverted_index":{"As":[0],"spoken":[1],"dialogue":[2,28],"systems":[3],"become":[4],"deployed":[5],"in":[6,37],"increasingly":[7],"complex":[8],"domains,":[9],"they":[10],"face":[11],"rising":[12],"demands":[13],"on":[14,21],"the":[15,85,103],"naturalness":[16],"of":[17,47,65,87,107],"interaction.":[18],"We":[19,41],"focus":[20],"system":[22,95],"responsiveness,":[23],"aiming":[24],"to":[25,56,81,111],"mimic":[26],"human-like":[27],"flow":[29],"control":[30,101],"by":[31],"predicting":[32],"speaker":[33],"changes":[34],"as":[35],"observed":[36],"real":[38],"human-human":[39],"conversations.":[40],"derive":[42],"an":[43],"instantaneous":[44],"vector":[45],"representation":[46],"pitch":[48],"variation":[49],"and":[50,79],"show":[51],"that":[52],"it":[53],"is":[54],"amenable":[55],"standard":[57],"acoustic":[58],"modeling":[59],"techniques.":[60],"Using":[61],"a":[62],"small":[63],"amount":[64],"automatically":[66],"labeled":[67],"data,":[68],"we":[69],"train":[70],"models":[71],"which":[72,110],"significantly":[73],"outperform":[74],"current":[75],"state-of-the-art":[76],"pause-only":[77],"systems,":[78],"replicate":[80],"within":[82],"1%":[83],"absolute":[84],"performance":[86],"our":[88],"previously":[89],"published":[90],"hand-crafted":[91],"baseline.":[92],"The":[93],"new":[94],"additionally":[96],"offers":[97],"scope":[98],"for":[99],"run-time":[100],"over":[102],"precision":[104],"or":[105],"recall":[106],"locations":[108],"at":[109],"speak.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
