{"id":"https://openalex.org/W4416798391","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249381","title":"A Distilled Low-Latency Neural Vocoder with Explicit Amplitude and Phase Prediction","display_name":"A Distilled Low-Latency Neural Vocoder with Explicit Amplitude and Phase Prediction","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798391","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249381"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5067982618","display_name":"Hui-Peng Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui-Peng Du","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069176378","display_name":"Zhen-Hua Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17270295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"483","last_page":"488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.37290000915527344,"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":0.37290000915527344,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.24199999868869781,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.1965000033378601,"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/spectrogram","display_name":"Spectrogram","score":0.7346000075340271},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.546999990940094},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5253000259399414},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.49880000948905945},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.4066999852657318},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.3977000117301941},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3878999948501587},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.37470000982284546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566999793052673},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7346000075340271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6938999891281128},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.49880000948905945},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2545034164","display_name":null,"funder_award_id":"2308085QF200","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G5861301885","display_name":null,"funder_award_id":"62301521","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2963300588","https://openalex.org/W3197273793","https://openalex.org/W3215615641","https://openalex.org/W4221152438","https://openalex.org/W4225566824","https://openalex.org/W4225956675","https://openalex.org/W4372260127","https://openalex.org/W4372270198","https://openalex.org/W4377000449","https://openalex.org/W4385823126","https://openalex.org/W4386076493","https://openalex.org/W4391806982","https://openalex.org/W4392904136","https://openalex.org/W4394595435","https://openalex.org/W4399875170","https://openalex.org/W4401358097","https://openalex.org/W4402111239","https://openalex.org/W4408355663"],"related_works":[],"abstract_inverted_index":{"The":[0,82],"majority":[1],"of":[2,92,127],"mainstream":[3,164],"neural":[4,55,166],"vocoders":[5],"primarily":[6],"focus":[7],"on":[8,161],"speech":[9,74,104,143,159],"quality":[10,105,160,176],"and":[11,39,62,70,96,177],"generation":[12,126],"speed,":[13],"while":[14,148],"overlooking":[15],"latency,":[16],"which":[17,57],"is":[18,115],"a":[19,52,111,118],"critical":[20],"factor":[21],"in":[22,31],"real-time":[23,45],"applications.":[24],"Excessive":[25],"latency":[26],"leads":[27],"to":[28,88,94,171],"noticeable":[29],"delays":[30],"user":[32,37],"interaction,":[33],"severely":[34],"degrading":[35],"the":[36,60,73,90,128,137,154],"experience":[38],"rendering":[40],"such":[41],"systems":[42],"impractical":[43],"for":[44],"use.":[46],"Therefore,":[47],"this":[48],"paper":[49],"proposes":[50],"DLL-APNet,":[51],"Distilled":[53],"Low-Latency":[54],"vocoder":[56,84,122,140,157],"first":[58],"predicts":[59],"Amplitude":[61],"Phase":[63],"spectra":[64],"explicitly":[65],"from":[66],"input":[67],"mel":[68],"spectrogram":[69],"then":[71],"reconstructs":[72],"waveform":[75],"via":[76],"inverse":[77],"short-time":[78],"Fourier":[79],"transform":[80],"(iSTFT).":[81],"DLLAPNet":[83],"leverages":[85],"causal":[86,109,129,146],"convolutions":[87],"constrain":[89],"utilization":[91],"information":[93],"current":[95],"historical":[97],"contexts,":[98],"effectively":[99],"minimizing":[100],"latency.":[101,179],"To":[102],"mitigate":[103],"degradation":[106],"caused":[107],"by":[108],"constraints,":[110],"knowledge":[112],"distillation":[113],"strategy":[114],"proposed,":[116],"where":[117],"pre-trained":[119],"non-causal":[120,165],"teacher":[121],"guides":[123],"intermediate":[124],"feature":[125],"student":[130],"DLL-APNet":[131,139,156],"vocoder.":[132],"Experimental":[133],"results":[134],"demonstrate":[135],"that":[136],"proposed":[138,155],"produces":[141],"higher-quality":[142],"than":[144],"other":[145],"vocoders,":[147,167],"requiring":[149],"fewer":[150],"computational":[151],"resources.":[152],"Furthermore,":[153],"achieves":[158],"par":[162],"with":[163],"validating":[168],"its":[169],"ability":[170],"deliver":[172],"both":[173],"high":[174],"perceptual":[175],"low":[178]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}