{"id":"https://openalex.org/W2105958269","doi":"https://doi.org/10.1109/icassp.2011.5947574","title":"Speech synthesis using HMM based diphone inventory encoding for low-resource devices","display_name":"Speech synthesis using HMM based diphone inventory encoding for low-resource devices","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2105958269","doi":"https://doi.org/10.1109/icassp.2011.5947574","mag":"2105958269"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5036288322","display_name":"Guntram Strecha","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Guntram Strecha","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Germany","Technische Universitat Dresden, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"Technische Universitat Dresden, Germany#TAB#","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101784693","display_name":"Matthias Wolff","orcid":"https://orcid.org/0000-0002-3895-7313"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Wolff","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Germany","Technische Universitat Dresden, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"Technische Universitat Dresden, Germany#TAB#","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036288322"],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":0.9187,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74622397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5380","last_page":"5383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7701725363731384},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7201357483863831},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7147389054298401},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6826598644256592},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6774437427520752},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6054120063781738},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5654264688491821},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.44237181544303894},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.42465150356292725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3640329837799072},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35479629039764404},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.060990214347839355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701725363731384},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7201357483863831},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7147389054298401},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6826598644256592},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6774437427520752},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6054120063781738},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5654264688491821},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.44237181544303894},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.42465150356292725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3640329837799072},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35479629039764404},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.060990214347839355},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/W202170023","https://openalex.org/W1538023239","https://openalex.org/W1549169474","https://openalex.org/W2093450784","https://openalex.org/W2100868147","https://openalex.org/W2101047103","https://openalex.org/W2132353520","https://openalex.org/W2158942523","https://openalex.org/W6608243308"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W2377486419","https://openalex.org/W2943202426","https://openalex.org/W2736714427","https://openalex.org/W2038801705","https://openalex.org/W2136885550","https://openalex.org/W2688184458","https://openalex.org/W2904846757"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"describe":[4,70],"the":[5,12,30,53,56,61,71,75,80,86,106,113],"compression":[6,22],"of":[7,15,34,52,60,115],"diphone":[8,90],"inventories":[9,76,111,120],"used":[10],"by":[11,63],"acoustic":[13,81],"synthesis":[14,18,82,107,116],"a":[16,26,42,46,64,67,89],"concatenative":[17],"system.":[19],"The":[20,50],"inventory":[21,91,124],"is":[23,55],"based":[24],"on":[25],"codebook":[27],"drawn":[28],"from":[29],"Gaussian":[31],"mean":[32],"vectors":[33],"phoneme":[35],"HMMs.":[36],"There":[37],"are":[38],"two":[39],"encoding/synthesis":[40],"schemes,":[41],"speaker":[43,47],"dependent":[44],"and":[45,66],"independent":[48],"one.":[49],"advantage":[51],"latter":[54],"potential":[57],"common":[58],"use":[59],"HM-models":[62],"recognizer":[65],"synthesizer.":[68],"We":[69,102],"steps":[72],"to":[73,99],"encode":[74],"as":[77,79],"well":[78],"using":[83],"them.":[84],"Using":[85],"proposed":[87],"method":[88],"with":[92,109,117],"1175":[93],"units":[94],"can":[95],"be":[96],"compressed":[97],"down":[98],"19":[100],"kB.":[101],"will":[103],"show":[104],"that":[105],"quality":[108,114],"HMM-encoded":[110],"matches":[112],"AMRor":[118],"SPEEX-encoded":[119],"at":[121],"noticeably":[122],"smaller":[123],"sizes.":[125]},"counts_by_year":[{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}