{"id":"https://openalex.org/W2400227915","doi":"https://doi.org/10.21437/interspeech.2011-90","title":"Combining frame and segment level processing via temporal pooling for phonetic classification","display_name":"Combining frame and segment level processing via temporal pooling for phonetic classification","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2400227915","doi":"https://doi.org/10.21437/interspeech.2011-90","mag":"2400227915"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-90","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-90","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},"type":"article","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/A5078511139","display_name":"Sumit Chopra","orcid":"https://orcid.org/0009-0009-6637-2230"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sumit Chopra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026605560","display_name":"Patrick Haffner","orcid":"https://orcid.org/0000-0002-2319-5109"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Haffner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5115044944","display_name":"Dimitrios Dimitriadis","orcid":"https://orcid.org/0000-0001-8483-0105"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitrios Dimitriadis","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078511139"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32520203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"233","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9901999831199646,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9901999831199646,"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/T11309","display_name":"Music and Audio Processing","score":0.9653000235557556,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9377999901771545,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/pooling","display_name":"Pooling","score":0.8110228776931763},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7844998836517334},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.7192862033843994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5704617500305176},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5400887131690979},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4796219766139984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3536433279514313},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07285338640213013}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8110228776931763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7844998836517334},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.7192862033843994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5704617500305176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5400887131690979},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4796219766139984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3536433279514313},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07285338640213013}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2011-90","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-90","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.307.9414","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.307.9414","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/export/sites/att_labs/techdocs/TD_100455.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,31,70],"simple,":[3],"yet":[4],"novel,":[5],"multi-layer":[6],"model":[7,15,50,65],"for":[8],"the":[9,17,22,26,43,52,56],"problem":[10],"of":[11,21,40,45,63,72],"phonetic":[12,47],"classification.":[13],"Our":[14],"combines":[16],"frame":[18],"level":[19,28],"transformation":[20,29],"acoustic":[23],"signal":[24],"with":[25],"segment":[27],"via":[30],"temporal":[32],"pooling":[33,73],"architecture":[34],"to":[35,68,76],"compute":[36],"class":[37],"conditional":[38],"probabilities":[39],"phones.":[41],"Without":[42],"use":[44],"any":[46],"knowledge,":[48],"our":[49,64],"achieved":[51],"state-ofthe-art":[53],"performance":[54,79],"on":[55],"TIMIT":[57],"phone":[58,91],"classification":[59,92],"task.":[60],"The":[61],"flexibility":[62],"allows":[66],"us":[67],"mix":[69],"variety":[71],"architectures,":[74],"leading":[75],"further":[77],"significant":[78],"improvements.":[80],"Index":[81],"Terms:":[82],"deep":[83],"networks,":[84,86],"connectionist":[85],"multilayer":[87],"models,":[88],"ensemble":[89],"methods,":[90]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
