{"id":"https://openalex.org/W3205579917","doi":"https://doi.org/10.1109/icassp43922.2022.9746202","title":"PAMA-TTS: Progression-Aware Monotonic Attention for Stable SEQ2SEQ TTS with Accurate Phoneme Duration Control","display_name":"PAMA-TTS: Progression-Aware Monotonic Attention for Stable SEQ2SEQ TTS with Accurate Phoneme Duration Control","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205579917","doi":"https://doi.org/10.1109/icassp43922.2022.9746202","mag":"3205579917"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746202","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5059090577","display_name":"Yunchao He","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunchao He","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054843960","display_name":"Jian Luan","orcid":"https://orcid.org/0000-0002-2383-226X"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Luan","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362600","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0002-2165-2599"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059090577"],"corresponding_institution_ids":["https://openalex.org/I862669128"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.22128852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7467","last_page":"7471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/naturalness","display_name":"Naturalness","score":0.9083480834960938},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.8869653940200806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7010419368743896},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.6828984618186951},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6402502059936523},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6124067902565002},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5398086905479431},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4423207938671112},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4346632957458496},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42900368571281433},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.42385134100914},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42381545901298523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3655814528465271},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15634512901306152},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15521523356437683}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9083480834960938},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.8869653940200806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010419368743896},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.6828984618186951},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6402502059936523},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6124067902565002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5398086905479431},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4423207938671112},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4346632957458496},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42900368571281433},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.42385134100914},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42381545901298523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3655814528465271},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15634512901306152},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15521523356437683},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746202","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2886769154","https://openalex.org/W2903739847","https://openalex.org/W2942807473","https://openalex.org/W2946200149","https://openalex.org/W2963091184","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2971753973","https://openalex.org/W3007859642","https://openalex.org/W3015922793","https://openalex.org/W3016136182","https://openalex.org/W3025793647","https://openalex.org/W3033913438","https://openalex.org/W3091928890","https://openalex.org/W3096442195","https://openalex.org/W3130016944","https://openalex.org/W3149617007","https://openalex.org/W3161296985","https://openalex.org/W3197294703","https://openalex.org/W3197858274","https://openalex.org/W4287761884","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6739901393","https://openalex.org/W6763832098","https://openalex.org/W6767453231","https://openalex.org/W6779337556","https://openalex.org/W6784545093"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W2535215250","https://openalex.org/W2024201202"],"abstract_inverted_index":{"Sequence":[0],"expansion":[1],"between":[2],"encoder":[3],"and":[4,25,68,83],"decoder":[5],"is":[6],"a":[7,87,115],"critical":[8],"challenge":[9],"in":[10,49,93,114],"sequence-to-sequence":[11],"TTS.":[12],"Attention-based":[13],"methods":[14],"achieve":[15],"great":[16],"naturalness":[17],"but":[18,45,117],"suffer":[19],"from":[20],"unstable":[21],"issues":[22],"like":[23],"missing":[24],"repeating":[26],"phonemes,":[27],"not":[28],"to":[29,40,56,107],"mention":[30],"accurate":[31],"duration":[32,44,70,82,135],"control.":[33,119],"Duration-informed":[34],"methods,":[35],"on":[36,73],"the":[37,58,62,74,98,105,111,126,138],"contrary,":[38],"seem":[39],"easily":[41],"adjust":[42],"phoneme":[43,100],"show":[46],"obvious":[47],"degradation":[48],"speech":[50],"naturalness.":[51],"This":[52],"paper":[53],"proposes":[54],"PAMA-TTS":[55,78,124],"address":[57],"problem.":[59],"It":[60],"takes":[61],"advantage":[63],"of":[64,86],"both":[65],"flexible":[66],"attention":[67,76,106],"explicit":[69],"models.":[71],"Based":[72],"monotonic":[75],"mechanism,":[77],"also":[79],"leverages":[80],"token":[81,112],"relative":[84],"position":[85],"frame,":[88],"especially":[89],"countdown":[90],"information,":[91],"i.e.":[92],"how":[94],"many":[95],"future":[96],"frames":[97],"present":[99],"will":[101],"end.":[102],"They":[103],"help":[104],"move":[108],"forward":[109],"along":[110],"sequence":[113],"soft":[116],"reliable":[118],"Experimental":[120],"results":[121],"prove":[122],"that":[123],"achieves":[125],"highest":[127],"naturalness,":[128],"while":[129],"has":[130],"on-par":[131],"or":[132],"even":[133],"better":[134],"controllability":[136],"than":[137],"duration-informed":[139],"model.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}