Modeling Analog Dynamic Range Compressors using Deep Learning and State-space Models

We describe a novel approach for developing realistic digital models of dynamic range compressors for digital audio production by analyzing their analog prototypes. While realistic digital dynamic compressors are potentially useful for many applications, the design process is challenging because the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yin, Hanzhi, Cheng, Gang, Steinmetz, Christian J, Yuan, Ruibin, Stern, Richard M, Dannenberg, Roger B
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Yin, Hanzhi
Cheng, Gang
Steinmetz, Christian J
Yuan, Ruibin
Stern, Richard M
Dannenberg, Roger B
description We describe a novel approach for developing realistic digital models of dynamic range compressors for digital audio production by analyzing their analog prototypes. While realistic digital dynamic compressors are potentially useful for many applications, the design process is challenging because the compressors operate nonlinearly over long time scales. Our approach is based on the structured state space sequence model (S4), as implementing the state-space model (SSM) has proven to be efficient at learning long-range dependencies and is promising for modeling dynamic range compressors. We present in this paper a deep learning model with S4 layers to model the Teletronix LA-2A analog dynamic range compressor. The model is causal, executes efficiently in real time, and achieves roughly the same quality as previous deep-learning models but with fewer parameters.
doi_str_mv 10.48550/arxiv.2403.16331
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2403_16331</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2403_16331</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-89b32be7c97e630eb1243d13ad0a091ff283b919bb7c0ffed42a9295135f04103</originalsourceid><addsrcrecordid>eNotj81KxDAURrNxIaMP4Mq8QGuSm_5kOXT8g4qg3Zeb9qYU2rQkozhvL62uPg58HDiM3UmR6jLLxAOGn_E7VVpAKnMAec2at6WnafQDP3qcloGfLh7nseMf6Afi1TKvgWJcQuRfcbudiFZeEwa_Efqef57xTElcsSO-2-INu3I4Rbr93wNrnh6b6iWp359fq2OdYF7IpDQWlKWiMwXlIMhKpaGXgL1AYaRzqgRrpLG26IRz1GuFRplMQuaElgIO7P5Pu2e1axhnDJd2y2v3PPgFRipKQQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Modeling Analog Dynamic Range Compressors using Deep Learning and State-space Models</title><source>arXiv.org</source><creator>Yin, Hanzhi ; Cheng, Gang ; Steinmetz, Christian J ; Yuan, Ruibin ; Stern, Richard M ; Dannenberg, Roger B</creator><creatorcontrib>Yin, Hanzhi ; Cheng, Gang ; Steinmetz, Christian J ; Yuan, Ruibin ; Stern, Richard M ; Dannenberg, Roger B</creatorcontrib><description>We describe a novel approach for developing realistic digital models of dynamic range compressors for digital audio production by analyzing their analog prototypes. While realistic digital dynamic compressors are potentially useful for many applications, the design process is challenging because the compressors operate nonlinearly over long time scales. Our approach is based on the structured state space sequence model (S4), as implementing the state-space model (SSM) has proven to be efficient at learning long-range dependencies and is promising for modeling dynamic range compressors. We present in this paper a deep learning model with S4 layers to model the Teletronix LA-2A analog dynamic range compressor. The model is causal, executes efficiently in real time, and achieves roughly the same quality as previous deep-learning models but with fewer parameters.</description><identifier>DOI: 10.48550/arxiv.2403.16331</identifier><language>eng</language><subject>Computer Science - Learning ; Computer Science - Sound</subject><creationdate>2024-03</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2403.16331$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2403.16331$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Yin, Hanzhi</creatorcontrib><creatorcontrib>Cheng, Gang</creatorcontrib><creatorcontrib>Steinmetz, Christian J</creatorcontrib><creatorcontrib>Yuan, Ruibin</creatorcontrib><creatorcontrib>Stern, Richard M</creatorcontrib><creatorcontrib>Dannenberg, Roger B</creatorcontrib><title>Modeling Analog Dynamic Range Compressors using Deep Learning and State-space Models</title><description>We describe a novel approach for developing realistic digital models of dynamic range compressors for digital audio production by analyzing their analog prototypes. While realistic digital dynamic compressors are potentially useful for many applications, the design process is challenging because the compressors operate nonlinearly over long time scales. Our approach is based on the structured state space sequence model (S4), as implementing the state-space model (SSM) has proven to be efficient at learning long-range dependencies and is promising for modeling dynamic range compressors. We present in this paper a deep learning model with S4 layers to model the Teletronix LA-2A analog dynamic range compressor. The model is causal, executes efficiently in real time, and achieves roughly the same quality as previous deep-learning models but with fewer parameters.</description><subject>Computer Science - Learning</subject><subject>Computer Science - Sound</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81KxDAURrNxIaMP4Mq8QGuSm_5kOXT8g4qg3Zeb9qYU2rQkozhvL62uPg58HDiM3UmR6jLLxAOGn_E7VVpAKnMAec2at6WnafQDP3qcloGfLh7nseMf6Afi1TKvgWJcQuRfcbudiFZeEwa_Efqef57xTElcsSO-2-INu3I4Rbr93wNrnh6b6iWp359fq2OdYF7IpDQWlKWiMwXlIMhKpaGXgL1AYaRzqgRrpLG26IRz1GuFRplMQuaElgIO7P5Pu2e1axhnDJd2y2v3PPgFRipKQQ</recordid><startdate>20240324</startdate><enddate>20240324</enddate><creator>Yin, Hanzhi</creator><creator>Cheng, Gang</creator><creator>Steinmetz, Christian J</creator><creator>Yuan, Ruibin</creator><creator>Stern, Richard M</creator><creator>Dannenberg, Roger B</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240324</creationdate><title>Modeling Analog Dynamic Range Compressors using Deep Learning and State-space Models</title><author>Yin, Hanzhi ; Cheng, Gang ; Steinmetz, Christian J ; Yuan, Ruibin ; Stern, Richard M ; Dannenberg, Roger B</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-89b32be7c97e630eb1243d13ad0a091ff283b919bb7c0ffed42a9295135f04103</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Learning</topic><topic>Computer Science - Sound</topic><toplevel>online_resources</toplevel><creatorcontrib>Yin, Hanzhi</creatorcontrib><creatorcontrib>Cheng, Gang</creatorcontrib><creatorcontrib>Steinmetz, Christian J</creatorcontrib><creatorcontrib>Yuan, Ruibin</creatorcontrib><creatorcontrib>Stern, Richard M</creatorcontrib><creatorcontrib>Dannenberg, Roger B</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yin, Hanzhi</au><au>Cheng, Gang</au><au>Steinmetz, Christian J</au><au>Yuan, Ruibin</au><au>Stern, Richard M</au><au>Dannenberg, Roger B</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Modeling Analog Dynamic Range Compressors using Deep Learning and State-space Models</atitle><date>2024-03-24</date><risdate>2024</risdate><abstract>We describe a novel approach for developing realistic digital models of dynamic range compressors for digital audio production by analyzing their analog prototypes. While realistic digital dynamic compressors are potentially useful for many applications, the design process is challenging because the compressors operate nonlinearly over long time scales. Our approach is based on the structured state space sequence model (S4), as implementing the state-space model (SSM) has proven to be efficient at learning long-range dependencies and is promising for modeling dynamic range compressors. We present in this paper a deep learning model with S4 layers to model the Teletronix LA-2A analog dynamic range compressor. The model is causal, executes efficiently in real time, and achieves roughly the same quality as previous deep-learning models but with fewer parameters.</abstract><doi>10.48550/arxiv.2403.16331</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2403.16331
ispartof
issn
language eng
recordid cdi_arxiv_primary_2403_16331
source arXiv.org
subjects Computer Science - Learning
Computer Science - Sound
title Modeling Analog Dynamic Range Compressors using Deep Learning and State-space Models
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T18%3A47%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Modeling%20Analog%20Dynamic%20Range%20Compressors%20using%20Deep%20Learning%20and%20State-space%20Models&rft.au=Yin,%20Hanzhi&rft.date=2024-03-24&rft_id=info:doi/10.48550/arxiv.2403.16331&rft_dat=%3Carxiv_GOX%3E2403_16331%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true