{"id":"https://openalex.org/W2100953957","doi":"https://doi.org/10.1109/icassp.2003.1202349","title":"High performance speaker and vocabulary independent ASR technology for mobile phones","display_name":"High performance speaker and vocabulary independent ASR technology for mobile phones","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W2100953957","doi":"https://doi.org/10.1109/icassp.2003.1202349","mag":"2100953957"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1202349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202349","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5009183426","display_name":"Sergey Astrov","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"S. Astrov","raw_affiliation_strings":["Corporate Technology, Siemens AG, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Corporate Technology, Siemens AG, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045959815","display_name":"Jan Bauer","orcid":"https://orcid.org/0000-0002-0657-1213"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J.G. Bauer","raw_affiliation_strings":["Corporate Technology, Siemens AG, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Corporate Technology, Siemens AG, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042929024","display_name":"S. Stan","orcid":"https://orcid.org/0009-0005-2628-4712"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S. Stan","raw_affiliation_strings":["ICM Mobile Phones, Siemens AG, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"ICM Mobile Phones, Siemens AG, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009183426"],"corresponding_institution_ids":["https://openalex.org/I1325886976"],"apc_list":null,"apc_paid":null,"fwci":0.3853,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6038961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8144927024841309},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7873304486274719},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7861381769180298},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7035319805145264},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6815587282180786},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5874924659729004},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.5372839570045471},{"id":"https://openalex.org/keywords/microcontroller","display_name":"Microcontroller","score":0.46771353483200073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.325096070766449},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32398074865341187},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.28473973274230957},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.22088685631752014},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09810402989387512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144927024841309},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7873304486274719},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7861381769180298},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7035319805145264},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6815587282180786},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5874924659729004},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.5372839570045471},{"id":"https://openalex.org/C173018170","wikidata":"https://www.wikidata.org/wiki/Q165678","display_name":"Microcontroller","level":2,"score":0.46771353483200073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.325096070766449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32398074865341187},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.28473973274230957},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.22088685631752014},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09810402989387512},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1202349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202349","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W20163840","https://openalex.org/W67543304","https://openalex.org/W2098825707","https://openalex.org/W2142873456","https://openalex.org/W2145233332","https://openalex.org/W3140835062","https://openalex.org/W6600814045","https://openalex.org/W6602745767","https://openalex.org/W6681580746"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2102309991","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2535886977"],"abstract_inverted_index":{"This":[0,39],"paper":[1],"presents":[2],"the":[3,44,47,53,72,110,117],"Siemens":[4],"speech":[5],"recognizer":[6],"for":[7,43,85,138],"mobile":[8],"phones,":[9],"VSR.":[10],"VSR":[11,63,127],"employs":[12],"HMM":[13,93],"technology":[14],"and":[15,25,71],"uses":[16],"general-purpose":[17],"phoneme-based":[18],"acoustic":[19,94],"models":[20,95],"which":[21,50],"make":[22],"it":[23],"speaker":[24],"vocabulary":[26,77],"independent.":[27],"The":[28,59,67,92,104,133],"system":[29,60,125],"can":[30],"be":[31],"easily":[32],"reconfigured":[33],"to":[34],"work":[35],"with":[36,52,75,142],"arbitrary":[37],"vocabularies.":[38],"provides":[40],"full":[41],"flexibility":[42],"design":[45],"of":[46,55,62,78,101,116,124],"user":[48],"interface":[49],"contrasts":[51],"capabilities":[54],"other":[56],"low-resource":[57],"recognizers.":[58],"requirements":[61,121],"are":[64],"very":[65],"low.":[66],"emission":[68],"probability":[69],"calculation":[70],"Viterbi":[73],"search":[74],"a":[76,139],"30":[79],"words":[80,146],"need":[81],"only":[82],"16":[83],"MHz":[84],"real-time":[86],"operation":[87],"on":[88],"an":[89,129],"ARM":[90],"microcontroller.":[91],"take":[96],"up":[97],"about":[98],"12":[99],"kilobytes":[100],"permanent":[102],"storage.":[103],"most":[105],"significant":[106],"algorithmic":[107],"improvement":[108],"is":[109,151],"newly":[111],"developed":[112],"3-D":[113],"stream-based":[114],"coding":[115],"HMMs.":[118],"Despite":[119],"low":[120],"in":[122],"terms":[123],"resources":[126],"achieves":[128],"outstanding":[130],"recognition":[131,140],"performance.":[132],"word":[134],"error":[135],"rate":[136],"(WER)":[137],"task":[141],"62":[143],"German":[144],"isolated":[145],"including":[147],"highly":[148],"confusable":[149],"digits":[150],"7.0%.":[152]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}