{"id":"https://openalex.org/W7134267632","doi":"https://doi.org/10.1145/3742414.3794721","title":"From Speech to Action: Home Automation Speech Ensemble (HASE) and an Open Pipeline for Smart-Home Control","display_name":"From Speech to Action: Home Automation Speech Ensemble (HASE) and an Open Pipeline for Smart-Home Control","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134267632","doi":"https://doi.org/10.1145/3742414.3794721"},"language":null,"primary_location":{"id":"doi:10.1145/3742414.3794721","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742414.3794721","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3742414.3794721","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053626866","display_name":"Mathias Pelka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127057","display_name":"Technical University of Applied Sciences L\u00fcbeck","ror":"https://ror.org/032xqbj11","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210127057"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mathias Pelka","raw_affiliation_strings":["Technische Hochschule L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":"https://orcid.org/0009-0004-1118-5183","affiliations":[{"raw_affiliation_string":"Technische Hochschule L\u00fcbeck, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I4210127057"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5053626866"],"corresponding_institution_ids":["https://openalex.org/I4210127057"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48514478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8195000290870667,"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":0.8195000290870667,"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/T12031","display_name":"Speech and dialogue systems","score":0.020999999716877937,"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/T12222","display_name":"IoT-based Smart Home Systems","score":0.018400000408291817,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7820000052452087},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5662000179290771},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5630999803543091},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.5181999802589417},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4968000054359436},{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.47929999232292175},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.43939998745918274},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41019999980926514}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7820000052452087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138000130653381},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5662000179290771},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.5181999802589417},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4805999994277954},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.444599986076355},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C507571656","wikidata":"https://www.wikidata.org/wiki/Q848436","display_name":"Home automation","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.3750999867916107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3643999993801117},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C42357961","wikidata":"https://www.wikidata.org/wiki/Q213363","display_name":"Open set","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C67936045","wikidata":"https://www.wikidata.org/wiki/Q681263","display_name":"Open standard","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3742414.3794721","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742414.3794721","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3742414.3794721","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742414.3794721","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6526505947113037}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W4385572438","https://openalex.org/W4386171319","https://openalex.org/W4411119167","https://openalex.org/W4413237817"],"related_works":[],"abstract_inverted_index":{"How":[0],"hard":[1],"is":[2],"it":[3,21],"to":[4,8,31,90,108,152],"set":[5],"the":[6,14,54,116,141,159],"heating":[7],"19":[9],"degrees":[10],"or":[11],"turn":[12],"on":[13],"light":[15],"with":[16,67,85],"your":[17],"voice?":[18],"Harder":[19],"than":[20],"sounds:":[22],"spoken":[23,65],"home-automation":[24],"commands":[25,66],"must":[26],"be":[27],"transcribed":[28],"and":[29,39,46,70,73,103,114,137,148,155],"mapped":[30],"an":[32,60,86],"unambiguous,":[33],"machine-executable":[34],"representation,":[35],"but":[36],"recognition":[37,84],"errors":[38],"off-schema":[40],"parsing":[41],"often":[42],"break":[43],"this":[44],"chain":[45],"open":[47,61,76,118,143],"speech-to-action":[48],"benchmarks":[49],"remain":[50],"scarce.":[51],"We":[52,97],"introduce":[53],"Home":[55],"Automation":[56],"Speech":[57],"Ensemble":[58],"(HASE),":[59],"dataset":[62],"of":[63],"700":[64],"gold":[68,71],"transcripts":[69],"sequences,":[72],"a":[74,92,125],"fully":[75],"two-stage":[77],"pipeline":[78],"that":[79],"combines":[80],"local":[81],"automatic":[82],"speech":[83],"instruction-tuned":[87,105],"language":[88],"model":[89],"produce":[91],"single":[93],"schema-valid":[94],"JSON":[95],"command.":[96],"benchmark":[98],"seven":[99],"ASR":[100],"back":[101],"ends":[102],"ten":[104],"LLMs":[106],"(up":[107],"8B":[109],"parameters)":[110],"under":[111],"few-shot":[112],"prompting,":[113],"compare":[115],"best":[117,142],"stack":[119,144],"(Whisper":[120],"large-v2":[121],"+":[122,130],"Qwen3-4B-Instruct-2507)":[123],"against":[124],"representative":[126],"commercial":[127,160],"baseline":[128],"(GPT-4o-transcribe":[129],"GPT-4o-mini)":[131],"using":[132],"deployment-oriented":[133],"metrics":[134],"including":[135],"EEM":[136,147,154],"SMR.":[138],"On":[139],"HASE,":[140],"reaches":[145],"0.778":[146],"0.888":[149],"SMR,":[150],"compared":[151],"0.818":[153],"0.910":[156],"SMR":[157],"for":[158],"baseline.":[161]},"counts_by_year":[],"updated_date":"2026-03-10T14:13:21.323994","created_date":"2026-03-10T00:00:00"}
