{"id":"https://openalex.org/W2889345957","doi":"https://doi.org/10.21437/interspeech.2018-46","title":"Dithered Quantization for Frequency-Domain Speech and Audio Coding","display_name":"Dithered Quantization for Frequency-Domain Speech and Audio Coding","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889345957","doi":"https://doi.org/10.21437/interspeech.2018-46","mag":"2889345957"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-46","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/357254e9-7baf-46a2-a64a-c1bce54a06fd","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052130850","display_name":"Tom B\u00e4ckstr\u00f6m","orcid":"https://orcid.org/0000-0002-5590-2349"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tom B\u00e4ckstr\u00f6m","raw_affiliation_strings":["Aalto University, Department of Signal Processing and Acoustics, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Department of Signal Processing and Acoustics, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055443993","display_name":"Johannes Fischer","orcid":"https://orcid.org/0000-0002-3384-597X"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Fischer","raw_affiliation_strings":["International Audio Laboratories Erlangen, Friedrich-Alexander University (FAU), Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Friedrich-Alexander University (FAU), Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035293526","display_name":"Sneha Das","orcid":"https://orcid.org/0000-0002-4017-1280"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sneha Das","raw_affiliation_strings":["Aalto University, Department of Signal Processing and Acoustics, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Department of Signal Processing and Acoustics, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6085,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80127045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3533","last_page":"3537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9998999834060669,"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":0.9983999729156494,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9944999814033508,"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/dither","display_name":"Dither","score":0.749060332775116},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.7320019602775574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6444377303123474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6304138898849487},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5880447626113892},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5223756432533264},{"id":"https://openalex.org/keywords/sub-band-coding","display_name":"Sub-band coding","score":0.4997718334197998},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.422532320022583},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40539494156837463},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.25689172744750977},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11471092700958252},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07583856582641602},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07093554735183716}],"concepts":[{"id":"https://openalex.org/C70451592","wikidata":"https://www.wikidata.org/wiki/Q376493","display_name":"Dither","level":3,"score":0.749060332775116},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.7320019602775574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6444377303123474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6304138898849487},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5880447626113892},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5223756432533264},{"id":"https://openalex.org/C98526533","wikidata":"https://www.wikidata.org/wiki/Q1691938","display_name":"Sub-band coding","level":3,"score":0.4997718334197998},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.422532320022583},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40539494156837463},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25689172744750977},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11471092700958252},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07583856582641602},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07093554735183716},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-46","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/34985","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/357254e9-7baf-46a2-a64a-c1bce54a06fd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/34985","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/357254e9-7baf-46a2-a64a-c1bce54a06fd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1545139949","https://openalex.org/W1577541836","https://openalex.org/W1580872065","https://openalex.org/W1634005169","https://openalex.org/W2115942321","https://openalex.org/W2396999047","https://openalex.org/W2514594265","https://openalex.org/W2566983320","https://openalex.org/W2616492649","https://openalex.org/W2758579457","https://openalex.org/W2964073500"],"related_works":["https://openalex.org/W2980446847","https://openalex.org/W187353244","https://openalex.org/W2011561032","https://openalex.org/W2118305611","https://openalex.org/W1857623347","https://openalex.org/W1999835922","https://openalex.org/W2744599249","https://openalex.org/W2336887028","https://openalex.org/W2496295964","https://openalex.org/W2111280847"],"abstract_inverted_index":{"A":[0],"common":[1],"issue":[2],"in":[3,8,113],"coding":[4,91],"speech":[5],"and":[6,41,46,83,137],"audio":[7],"the":[9,52,61,65,102,121,128,141,144],"frequency":[10],"domain,":[11],"which":[12,34],"appears":[13],"with":[14],"decreasing":[15],"bitrate,":[16],"is":[17],"that":[18,120],"quantization":[19,112],"levels":[20],"become":[21],"increasingly":[22],"sparse.":[23],"With":[24],"low":[25,68],"accuracy,":[26],"high-frequency":[27],"components":[28],"are":[29,85,96],"typically":[30],"quantized":[31,97],"to":[32,36,50,70,127],"zero,":[33],"leads":[35],"a":[37,89,114,132],"muffled":[38],"output":[39,122],"signal":[40,69],"musical":[42],"noise.":[43],"Band-width":[44],"extension":[45],"noise-filling":[47],"methods":[48,74],"attempt":[49],"treat":[51],"problem":[53],"by":[54],"inserting":[55],"noise":[56,71],"of":[57,67,101,143],"similar":[58],"energy":[59,84,123],"as":[60],"original":[62],"signal,":[63],"at":[64],"cost":[66],"ratio.":[72],"Dithering":[73],"however":[75],"provide":[76],"an":[77],"alternative":[78],"approach,":[79],"where":[80,93],"both":[81],"accuracy":[82],"retained.":[86],"We":[87,117],"propose":[88],"hybrid":[90],"approach":[92],"low-energy":[94],"samples":[95],"using":[98,131],"dithering,":[99,107],"instead":[100],"conventional":[103],"uniform":[104],"quantizer.":[105],"For":[106],"we":[108],"apply":[109],"1":[110],"bit":[111],"randomized":[115],"sub-space.":[116],"further":[118],"show":[119],"can":[124],"be":[125],"adjusted":[126],"desired":[129],"level":[130],"scaling":[133],"parameter.":[134],"Objective":[135],"measurements":[136],"listening":[138],"tests":[139],"demonstrate":[140],"advantages":[142],"proposed":[145],"methods.":[146]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
