Loading…

Regularized Linear Prediction of Speech

All-pole spectral envelope estimates based on linear prediction (LP) for speech signals often exhibit unnaturally sharp peaks, especially for high-pitch speakers. In this paper, regularization is used to penalize rapid changes in the spectral envelope, which improves the spectral envelope estimate....

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on audio, speech, and language processing speech, and language processing, 2008-01, Vol.16 (1), p.65-73
Main Authors:	Ekman, L.A., Kleijn, W.B., Murthi, M.N.
Format:	Article
Language:	English
Subjects:	Applied sciences Autocorrelation Bandwidth Bandwidth expansion Computational complexity Contamination Distortion envelope estimation Envelopes Estimates Exact sciences and technology Frequency Information, signal and communications theory Linear prediction linear prediction (LP) Natural language processing Predictive models Regularization Research and development Sampling methods Signal and communications theory Signal processing Signal representation. Spectral analysis Signal, noise Speaker recognition Spectra Speech Speech coding Speech processing Telecommunications and information theory
Citations:	Items that this one cites Items that cite this one
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

cited_by	cdi_FETCH-LOGICAL-c383t-21fd08d3c08310fb5de10405b50f012760a6b842c0ca2751926cecd0c45bfa9c3
cites	cdi_FETCH-LOGICAL-c383t-21fd08d3c08310fb5de10405b50f012760a6b842c0ca2751926cecd0c45bfa9c3
container_end_page	73
container_issue	1
container_start_page	65
container_title	IEEE transactions on audio, speech, and language processing
container_volume	16
creator	Ekman, L.A. Kleijn, W.B. Murthi, M.N.
description	All-pole spectral envelope estimates based on linear prediction (LP) for speech signals often exhibit unnaturally sharp peaks, especially for high-pitch speakers. In this paper, regularization is used to penalize rapid changes in the spectral envelope, which improves the spectral envelope estimate. Based on extensive experimental evidence, we conclude that regularized linear prediction outperforms bandwidth-expanded linear prediction. The regularization approach gives lower spectral distortion on average, and fewer outliers, while maintaining a very low computational complexity.
doi_str_mv	10.1109/TASL.2007.909448
format	article
fullrecord	<record><control><sourceid>proquest_pasca</sourceid><recordid>TN_cdi_pascalfrancis_primary_19954844</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4378273</ieee_id><sourcerecordid>36342215</sourcerecordid><originalsourceid>FETCH-LOGICAL-c383t-21fd08d3c08310fb5de10405b50f012760a6b842c0ca2751926cecd0c45bfa9c3</originalsourceid><addsrcrecordid>eNp9kE1Lw0AQhoMoWKt3wUsQtKfU2e_doxS_IKDYel42m11NSZO62xz015uSUsGDpxmY5x1mniQ5RzBFCNTN4naeTzGAmCpQlMqDZIQYk5lQmB7ue8SPk5MYlwCUcIpGyeTVvXe1CdW3K9O8apwJ6UtwZWU3VdukrU_na-fsx2ly5E0d3dmujpO3-7vF7DHLnx-eZrd5ZokkmwwjX4IsiQVJEPiClQ4BBVYw8ICw4GB4ISm2YA0WDCnMrbMlWMoKb5Ql42Qy7F2H9rNzcaNXVbSurk3j2i5qKRhQxSjqyet_ScIJxRixHrz8Ay7bLjT9F1ohQYFzSXoIBsiGNsbgvF6HamXCl0agt4L1VrDeCtaD4D5ytdtrojW1D6axVfzNqf5MSWnPXQxc5ZzbjykREgtCfgC924D7</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>917406683</pqid></control><display><type>article</type><title>Regularized Linear Prediction of Speech</title><source>IEEE Xplore (Online service)</source><creator>Ekman, L.A. ; Kleijn, W.B. ; Murthi, M.N.</creator><creatorcontrib>Ekman, L.A. ; Kleijn, W.B. ; Murthi, M.N.</creatorcontrib><description>All-pole spectral envelope estimates based on linear prediction (LP) for speech signals often exhibit unnaturally sharp peaks, especially for high-pitch speakers. In this paper, regularization is used to penalize rapid changes in the spectral envelope, which improves the spectral envelope estimate. Based on extensive experimental evidence, we conclude that regularized linear prediction outperforms bandwidth-expanded linear prediction. The regularization approach gives lower spectral distortion on average, and fewer outliers, while maintaining a very low computational complexity.</description><identifier>ISSN: 1558-7916</identifier><identifier>ISSN: 2329-9290</identifier><identifier>EISSN: 1558-7924</identifier><identifier>EISSN: 2329-9304</identifier><identifier>DOI: 10.1109/TASL.2007.909448</identifier><identifier>CODEN: ITASD8</identifier><language>eng</language><publisher>Piscataway, NJ: IEEE</publisher><subject>Applied sciences ; Autocorrelation ; Bandwidth ; Bandwidth expansion ; Computational complexity ; Contamination ; Distortion ; envelope estimation ; Envelopes ; Estimates ; Exact sciences and technology ; Frequency ; Information, signal and communications theory ; Linear prediction ; linear prediction (LP) ; Natural language processing ; Predictive models ; Regularization ; Research and development ; Sampling methods ; Signal and communications theory ; Signal processing ; Signal representation. Spectral analysis ; Signal, noise ; Speaker recognition ; Spectra ; Speech ; Speech coding ; Speech processing ; Telecommunications and information theory</subject><ispartof>IEEE transactions on audio, speech, and language processing, 2008-01, Vol.16 (1), p.65-73</ispartof><rights>2008 INIST-CNRS</rights><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2008</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c383t-21fd08d3c08310fb5de10405b50f012760a6b842c0ca2751926cecd0c45bfa9c3</citedby><cites>FETCH-LOGICAL-c383t-21fd08d3c08310fb5de10405b50f012760a6b842c0ca2751926cecd0c45bfa9c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4378273$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,4024,27923,27924,27925,54796</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=19954844$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Ekman, L.A.</creatorcontrib><creatorcontrib>Kleijn, W.B.</creatorcontrib><creatorcontrib>Murthi, M.N.</creatorcontrib><title>Regularized Linear Prediction of Speech</title><title>IEEE transactions on audio, speech, and language processing</title><addtitle>TASL</addtitle><description>All-pole spectral envelope estimates based on linear prediction (LP) for speech signals often exhibit unnaturally sharp peaks, especially for high-pitch speakers. In this paper, regularization is used to penalize rapid changes in the spectral envelope, which improves the spectral envelope estimate. Based on extensive experimental evidence, we conclude that regularized linear prediction outperforms bandwidth-expanded linear prediction. The regularization approach gives lower spectral distortion on average, and fewer outliers, while maintaining a very low computational complexity.</description><subject>Applied sciences</subject><subject>Autocorrelation</subject><subject>Bandwidth</subject><subject>Bandwidth expansion</subject><subject>Computational complexity</subject><subject>Contamination</subject><subject>Distortion</subject><subject>envelope estimation</subject><subject>Envelopes</subject><subject>Estimates</subject><subject>Exact sciences and technology</subject><subject>Frequency</subject><subject>Information, signal and communications theory</subject><subject>Linear prediction</subject><subject>linear prediction (LP)</subject><subject>Natural language processing</subject><subject>Predictive models</subject><subject>Regularization</subject><subject>Research and development</subject><subject>Sampling methods</subject><subject>Signal and communications theory</subject><subject>Signal processing</subject><subject>Signal representation. Spectral analysis</subject><subject>Signal, noise</subject><subject>Speaker recognition</subject><subject>Spectra</subject><subject>Speech</subject><subject>Speech coding</subject><subject>Speech processing</subject><subject>Telecommunications and information theory</subject><issn>1558-7916</issn><issn>2329-9290</issn><issn>1558-7924</issn><issn>2329-9304</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2008</creationdate><recordtype>article</recordtype><recordid>eNp9kE1Lw0AQhoMoWKt3wUsQtKfU2e_doxS_IKDYel42m11NSZO62xz015uSUsGDpxmY5x1mniQ5RzBFCNTN4naeTzGAmCpQlMqDZIQYk5lQmB7ue8SPk5MYlwCUcIpGyeTVvXe1CdW3K9O8apwJ6UtwZWU3VdukrU_na-fsx2ly5E0d3dmujpO3-7vF7DHLnx-eZrd5ZokkmwwjX4IsiQVJEPiClQ4BBVYw8ICw4GB4ISm2YA0WDCnMrbMlWMoKb5Ql42Qy7F2H9rNzcaNXVbSurk3j2i5qKRhQxSjqyet_ScIJxRixHrz8Ay7bLjT9F1ohQYFzSXoIBsiGNsbgvF6HamXCl0agt4L1VrDeCtaD4D5ytdtrojW1D6axVfzNqf5MSWnPXQxc5ZzbjykREgtCfgC924D7</recordid><startdate>200801</startdate><enddate>200801</enddate><creator>Ekman, L.A.</creator><creator>Kleijn, W.B.</creator><creator>Murthi, M.N.</creator><general>IEEE</general><general>Institute of Electrical and Electronics Engineers</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>200801</creationdate><title>Regularized Linear Prediction of Speech</title><author>Ekman, L.A. ; Kleijn, W.B. ; Murthi, M.N.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c383t-21fd08d3c08310fb5de10405b50f012760a6b842c0ca2751926cecd0c45bfa9c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Applied sciences</topic><topic>Autocorrelation</topic><topic>Bandwidth</topic><topic>Bandwidth expansion</topic><topic>Computational complexity</topic><topic>Contamination</topic><topic>Distortion</topic><topic>envelope estimation</topic><topic>Envelopes</topic><topic>Estimates</topic><topic>Exact sciences and technology</topic><topic>Frequency</topic><topic>Information, signal and communications theory</topic><topic>Linear prediction</topic><topic>linear prediction (LP)</topic><topic>Natural language processing</topic><topic>Predictive models</topic><topic>Regularization</topic><topic>Research and development</topic><topic>Sampling methods</topic><topic>Signal and communications theory</topic><topic>Signal processing</topic><topic>Signal representation. Spectral analysis</topic><topic>Signal, noise</topic><topic>Speaker recognition</topic><topic>Spectra</topic><topic>Speech</topic><topic>Speech coding</topic><topic>Speech processing</topic><topic>Telecommunications and information theory</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ekman, L.A.</creatorcontrib><creatorcontrib>Kleijn, W.B.</creatorcontrib><creatorcontrib>Murthi, M.N.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) Online</collection><collection>IEEE Xplore</collection><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on audio, speech, and language processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ekman, L.A.</au><au>Kleijn, W.B.</au><au>Murthi, M.N.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Regularized Linear Prediction of Speech</atitle><jtitle>IEEE transactions on audio, speech, and language processing</jtitle><stitle>TASL</stitle><date>2008-01</date><risdate>2008</risdate><volume>16</volume><issue>1</issue><spage>65</spage><epage>73</epage><pages>65-73</pages><issn>1558-7916</issn><issn>2329-9290</issn><eissn>1558-7924</eissn><eissn>2329-9304</eissn><coden>ITASD8</coden><abstract>All-pole spectral envelope estimates based on linear prediction (LP) for speech signals often exhibit unnaturally sharp peaks, especially for high-pitch speakers. In this paper, regularization is used to penalize rapid changes in the spectral envelope, which improves the spectral envelope estimate. Based on extensive experimental evidence, we conclude that regularized linear prediction outperforms bandwidth-expanded linear prediction. The regularization approach gives lower spectral distortion on average, and fewer outliers, while maintaining a very low computational complexity.</abstract><cop>Piscataway, NJ</cop><pub>IEEE</pub><doi>10.1109/TASL.2007.909448</doi><tpages>9</tpages></addata></record>
fulltext	fulltext
identifier	ISSN: 1558-7916
ispartof	IEEE transactions on audio, speech, and language processing, 2008-01, Vol.16 (1), p.65-73
issn	1558-7916 2329-9290 1558-7924 2329-9304
language	eng
recordid	cdi_pascalfrancis_primary_19954844
source	IEEE Xplore (Online service)
subjects	Applied sciences Autocorrelation Bandwidth Bandwidth expansion Computational complexity Contamination Distortion envelope estimation Envelopes Estimates Exact sciences and technology Frequency Information, signal and communications theory Linear prediction linear prediction (LP) Natural language processing Predictive models Regularization Research and development Sampling methods Signal and communications theory Signal processing Signal representation. Spectral analysis Signal, noise Speaker recognition Spectra Speech Speech coding Speech processing Telecommunications and information theory
title	Regularized Linear Prediction of Speech
url	http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T10%3A05%3A52IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pasca&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Regularized%20Linear%20Prediction%20of%20Speech&rft.jtitle=IEEE%20transactions%20on%20audio,%20speech,%20and%20language%20processing&rft.au=Ekman,%20L.A.&rft.date=2008-01&rft.volume=16&rft.issue=1&rft.spage=65&rft.epage=73&rft.pages=65-73&rft.issn=1558-7916&rft.eissn=1558-7924&rft.coden=ITASD8&rft_id=info:doi/10.1109/TASL.2007.909448&rft_dat=%3Cproquest_pasca%3E36342215%3C/proquest_pasca%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c383t-21fd08d3c08310fb5de10405b50f012760a6b842c0ca2751926cecd0c45bfa9c3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=917406683&rft_id=info:pmid/&rft_ieee_id=4378273&rfr_iscdi=true