{"id":"https://openalex.org/W2116994282","doi":"https://doi.org/10.1109/icassp.2009.4960552","title":"Combining mixture weight pruning and quantization for small-footprint speech recognition","display_name":"Combining mixture weight pruning and quantization for small-footprint speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2116994282","doi":"https://doi.org/10.1109/icassp.2009.4960552","mag":"2116994282"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5027165641","display_name":"David Huggins-Daines","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Huggins-Daines","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie Mellon University, Language Technologies Institute, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Language Technologies Institute, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040668817","display_name":"Alexander I. Rudnicky","orcid":"https://orcid.org/0000-0003-2044-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander I. Rudnicky","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie Mellon University, Language Technologies Institute, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Language Technologies Institute, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027165641"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.4516,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74398986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4189","last_page":"4192"},"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":0.9975000023841858,"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":0.9969000220298767,"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/codebook","display_name":"Codebook","score":0.8573178052902222},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.66801518201828},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6331449151039124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6165334582328796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6077561378479004},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6055917739868164},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5813880562782288},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5749931335449219},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5412859320640564},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5138090252876282},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47755131125450134},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.47419077157974243},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4110240638256073},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3583679795265198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3557456135749817}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8573178052902222},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.66801518201828},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6331449151039124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6165334582328796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6077561378479004},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6055917739868164},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5813880562782288},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5749931335449219},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5412859320640564},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5138090252876282},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47755131125450134},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.47419077157974243},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4110240638256073},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3583679795265198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3557456135749817},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.535.2016","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.535.2016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~dhuggins/Publications/mixw_quant.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1480366595","https://openalex.org/W1600901269","https://openalex.org/W2013196554","https://openalex.org/W2024490156","https://openalex.org/W2142873456","https://openalex.org/W2156885227","https://openalex.org/W2282029110"],"related_works":["https://openalex.org/W2148772884","https://openalex.org/W2017514583","https://openalex.org/W2100120615","https://openalex.org/W2352648934","https://openalex.org/W1929869830","https://openalex.org/W2017401491","https://openalex.org/W2387054321","https://openalex.org/W2012827167","https://openalex.org/W2062765737","https://openalex.org/W2391875658"],"abstract_inverted_index":{"Semi-continuous":[0],"acoustic":[1],"models,":[2],"where":[3],"the":[4,35,38,69,72],"output":[5],"distributions":[6],"for":[7,27],"all":[8],"Hidden":[9],"Markov":[10],"Model":[11],"states":[12],"share":[13],"a":[14,22,61],"common":[15],"codebook":[16],"of":[17,37,71],"Gaussian":[18],"density":[19],"functions,":[20],"are":[21],"well-known":[23],"and":[24,41,78],"proven":[25],"technique":[26,66],"reducing":[28],"computation":[29],"in":[30,81],"automatic":[31],"speech":[32],"recognition.":[33],"However,":[34],"size":[36,70],"parameter":[39],"files,":[40],"thus":[42],"their":[43],"memory":[44],"footprint":[45],"at":[46],"runtime,":[47],"can":[48,57],"be":[49,58],"very":[50],"large.":[51],"We":[52],"demonstrate":[53],"how":[54],"non-linear":[55],"quantization":[56],"combined":[59],"with":[60,74],"mixture":[62],"weight":[63],"distribution":[64],"pruning":[65],"to":[67],"halve":[68],"models":[73],"minimal":[75],"performance":[76],"overhead":[77],"no":[79],"increase":[80],"error":[82],"rate.":[83]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}