Loading…
Speech decoloration based on the product-of-filters model
We present a single-channel speech decoloration method based on a recently proposed generative product-of-filters (PoF) model. We take a spectral approach and attempt to learn the magnitude response of the actual coloration filter, given only the degraded speech signal. Experiments on synthetic data...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 2404 |
| container_issue | |
| container_start_page | 2400 |
| container_title | |
| container_volume | |
| creator | Dawen Liang Ellis, Daniel P. W. Hoffman, Matthew D. Mysore, Gautham J. |
| description | We present a single-channel speech decoloration method based on a recently proposed generative product-of-filters (PoF) model. We take a spectral approach and attempt to learn the magnitude response of the actual coloration filter, given only the degraded speech signal. Experiments on synthetic data demonstrate that the proposed method effectively captures both coarse and fine structure of the coloration filter. On real recordings, we find that simply subtracting the learned coloration filter from the log-spectra yields promising decoloration results. |
| doi_str_mv | 10.1109/ICASSP.2014.6854030 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_6854030</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6854030</ieee_id><sourcerecordid>6854030</sourcerecordid><originalsourceid>FETCH-LOGICAL-i220t-2d5e24ecc399f05704f5c640e9b197339e0982dec3a0d0fbe8533752a98ef5613</originalsourceid><addsrcrecordid>eNotj81KxDAUhaMoWMd5gtn0BVJv_prcpQzqCAMKVXA3pMkNU-mY0taFb2_BWZ2z-s53GNsIqIQAvH_ZPjTNWyVB6Kp2RoOCC7ZG64S2iNKh0peskMoiFwifV6wQRgKvhcYbdjtNXwDgrHYFw2YgCscyUsh9Hv3c5e-y9RPFcinzkcphzPEnzDwnnrp-pnEqTzlSf8euk-8nWp9zxT6eHt-3O75_fV789ryTEmYuoyGpKQSFmMBY0MmEWgNhK9AqhQTo5DKvPERILTmjlDXSo6NkaqFWbPPP7YjoMIzdyY-_h_Nr9QdDg0kt</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Speech decoloration based on the product-of-filters model</title><source>IEEE Xplore All Conference Series</source><creator>Dawen Liang ; Ellis, Daniel P. W. ; Hoffman, Matthew D. ; Mysore, Gautham J.</creator><creatorcontrib>Dawen Liang ; Ellis, Daniel P. W. ; Hoffman, Matthew D. ; Mysore, Gautham J.</creatorcontrib><description>We present a single-channel speech decoloration method based on a recently proposed generative product-of-filters (PoF) model. We take a spectral approach and attempt to learn the magnitude response of the actual coloration filter, given only the degraded speech signal. Experiments on synthetic data demonstrate that the proposed method effectively captures both coarse and fine structure of the coloration filter. On real recordings, we find that simply subtracting the learned coloration filter from the log-spectra yields promising decoloration results.</description><identifier>ISSN: 1520-6149</identifier><identifier>EISSN: 2379-190X</identifier><identifier>EISBN: 9781479928934</identifier><identifier>EISBN: 1479928933</identifier><identifier>DOI: 10.1109/ICASSP.2014.6854030</identifier><language>eng</language><publisher>IEEE</publisher><subject>audio ; Bayesian modeling ; decoloration ; Graphical models ; Radio frequency ; Reverberation ; Speech ; Speech enhancement ; variational inference</subject><ispartof>2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014, p.2400-2404</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6854030$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6854030$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Dawen Liang</creatorcontrib><creatorcontrib>Ellis, Daniel P. W.</creatorcontrib><creatorcontrib>Hoffman, Matthew D.</creatorcontrib><creatorcontrib>Mysore, Gautham J.</creatorcontrib><title>Speech decoloration based on the product-of-filters model</title><title>2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</title><addtitle>ICASSP</addtitle><description>We present a single-channel speech decoloration method based on a recently proposed generative product-of-filters (PoF) model. We take a spectral approach and attempt to learn the magnitude response of the actual coloration filter, given only the degraded speech signal. Experiments on synthetic data demonstrate that the proposed method effectively captures both coarse and fine structure of the coloration filter. On real recordings, we find that simply subtracting the learned coloration filter from the log-spectra yields promising decoloration results.</description><subject>audio</subject><subject>Bayesian modeling</subject><subject>decoloration</subject><subject>Graphical models</subject><subject>Radio frequency</subject><subject>Reverberation</subject><subject>Speech</subject><subject>Speech enhancement</subject><subject>variational inference</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9781479928934</isbn><isbn>1479928933</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2014</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj81KxDAUhaMoWMd5gtn0BVJv_prcpQzqCAMKVXA3pMkNU-mY0taFb2_BWZ2z-s53GNsIqIQAvH_ZPjTNWyVB6Kp2RoOCC7ZG64S2iNKh0peskMoiFwifV6wQRgKvhcYbdjtNXwDgrHYFw2YgCscyUsh9Hv3c5e-y9RPFcinzkcphzPEnzDwnnrp-pnEqTzlSf8euk-8nWp9zxT6eHt-3O75_fV789ryTEmYuoyGpKQSFmMBY0MmEWgNhK9AqhQTo5DKvPERILTmjlDXSo6NkaqFWbPPP7YjoMIzdyY-_h_Nr9QdDg0kt</recordid><startdate>20140101</startdate><enddate>20140101</enddate><creator>Dawen Liang</creator><creator>Ellis, Daniel P. W.</creator><creator>Hoffman, Matthew D.</creator><creator>Mysore, Gautham J.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20140101</creationdate><title>Speech decoloration based on the product-of-filters model</title><author>Dawen Liang ; Ellis, Daniel P. W. ; Hoffman, Matthew D. ; Mysore, Gautham J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i220t-2d5e24ecc399f05704f5c640e9b197339e0982dec3a0d0fbe8533752a98ef5613</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2014</creationdate><topic>audio</topic><topic>Bayesian modeling</topic><topic>decoloration</topic><topic>Graphical models</topic><topic>Radio frequency</topic><topic>Reverberation</topic><topic>Speech</topic><topic>Speech enhancement</topic><topic>variational inference</topic><toplevel>online_resources</toplevel><creatorcontrib>Dawen Liang</creatorcontrib><creatorcontrib>Ellis, Daniel P. W.</creatorcontrib><creatorcontrib>Hoffman, Matthew D.</creatorcontrib><creatorcontrib>Mysore, Gautham J.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Dawen Liang</au><au>Ellis, Daniel P. W.</au><au>Hoffman, Matthew D.</au><au>Mysore, Gautham J.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Speech decoloration based on the product-of-filters model</atitle><btitle>2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</btitle><stitle>ICASSP</stitle><date>2014-01-01</date><risdate>2014</risdate><spage>2400</spage><epage>2404</epage><pages>2400-2404</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><eisbn>9781479928934</eisbn><eisbn>1479928933</eisbn><abstract>We present a single-channel speech decoloration method based on a recently proposed generative product-of-filters (PoF) model. We take a spectral approach and attempt to learn the magnitude response of the actual coloration filter, given only the degraded speech signal. Experiments on synthetic data demonstrate that the proposed method effectively captures both coarse and fine structure of the coloration filter. On real recordings, we find that simply subtracting the learned coloration filter from the log-spectra yields promising decoloration results.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2014.6854030</doi><tpages>5</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-6149 |
| ispartof | 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014, p.2400-2404 |
| issn | 1520-6149 2379-190X |
| language | eng |
| recordid | cdi_ieee_primary_6854030 |
| source | IEEE Xplore All Conference Series |
| subjects | audio Bayesian modeling decoloration Graphical models Radio frequency Reverberation Speech Speech enhancement variational inference |
| title | Speech decoloration based on the product-of-filters model |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T01%3A03%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Speech%20decoloration%20based%20on%20the%20product-of-filters%20model&rft.btitle=2014%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech%20and%20Signal%20Processing%20(ICASSP)&rft.au=Dawen%20Liang&rft.date=2014-01-01&rft.spage=2400&rft.epage=2404&rft.pages=2400-2404&rft.issn=1520-6149&rft.eissn=2379-190X&rft_id=info:doi/10.1109/ICASSP.2014.6854030&rft.eisbn=9781479928934&rft.eisbn_list=1479928933&rft_dat=%3Cieee_CHZPO%3E6854030%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i220t-2d5e24ecc399f05704f5c640e9b197339e0982dec3a0d0fbe8533752a98ef5613%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6854030&rfr_iscdi=true |