--- title: Making machines that can listen | daily.dev description: MIT professor Paris Smaragdis builds machine learning systems that help computers hear and understand sound. His group works on machine learning for sound... canonical: https://daily.dev/posts/making-machines-that-can-listen-gj0jfeqrt twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Making machines that can listen | daily.dev og:description: MIT professor Paris Smaragdis builds machine learning systems that help computers hear and understand sound. His group works on machine learning for sound... og:url: https://daily.dev/posts/making-machines-that-can-listen-gj0jfeqrt og:image: https://api.daily.dev/og/posts/gJ0jfEqrT.png og:image:alt: Making machines that can listen og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Making machines that can listen **[MIT News](https://daily.dev/sources/mit)** · 8 min read · 0 upvotes · 0 comments ## Summary MIT professor Paris Smaragdis builds machine learning systems that help computers hear and understand sound. His group works on machine learning for sound source separation, tools for musicians, and fundamental audio processing. The group explores ways to incorporate large language models into speech recognition and audio enhancement. Earlier work on neural networks for separating individual sounds from audio mixtures caught the attention of the team on 'The Beatles: Get Back,' and he helped clean up archival recordings for it. His contributions helped the team win an Emmy for sound editing in 2022. His team has recently been exploring signal processing methods where sampling rates and frame sizes are not fixed. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What machine learning technique is used to separate individual sounds from a mixed audio recording? Neural networks can be trained to separate individual sounds from audio mixtures, an approach developed by researcher Paris Smaragdis and his group at the University of Illinois. This sound source separation technology was later used to help clean up archival Beatles recordings for the 2021 documentary mini-series 'The Beatles: Get Back,' contributing to an Emmy Award win for sound editing in 2022. _Developers building audio separation tools can follow machine learning research like this on daily.dev._ ## Similar posts on daily.dev - [Seeing sounds](https://daily.dev/posts/seeing-sounds-lko2p1khm) · MIT News · 0 upvotes · 0 comments - [SAM Audio](https://daily.dev/posts/sam-audio-zeewh9yc0) · Hacker News · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#mit](https://daily.dev/tags/mit), [#speech-recognition](https://daily.dev/tags/speech-recognition), [#audio-processing](https://daily.dev/tags/audio-processing) [View this post on daily.dev](https://daily.dev/posts/making-machines-that-can-listen-gj0jfeqrt) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Making machines that can listen","url":"https://daily.dev/posts/making-machines-that-can-listen-gj0jfeqrt","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/making-machines-that-can-listen-gj0jfeqrt"},"datePublished":"2026-10-28T04:04:45.506Z","dateModified":"2026-10-28T04:05:14.553Z","description":"MIT professor Paris Smaragdis builds machine learning systems that help computers hear and understand sound. His group works on machine learning for sound...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/dd13dc0b442e887aa7bf636d0a6932bd?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/dd13dc0b442e887aa7bf636d0a6932bd?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"MIT News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"MIT News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/881e20a40aa44b12ba4bd27f5c14289d","url":"https://daily.dev/sources/mit"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/making-machines-that-can-listen-gj0jfeqrt","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,mit,speech-recognition,audio-processing","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"MIT News","item":"https://daily.dev/sources/mit"},{"@type":"ListItem","position":3,"name":"Making machines that can listen"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/making-machines-that-can-listen-gj0jfeqrt#faq","mainEntity":[{"@type":"Question","name":"What machine learning technique is used to separate individual sounds from a mixed audio recording?","acceptedAnswer":{"@type":"Answer","text":"Neural networks can be trained to separate individual sounds from audio mixtures, an approach developed by researcher Paris Smaragdis and his group at the University of Illinois. This sound source separation technology was later used to help clean up archival Beatles recordings for the 2021 documentary mini-series 'The Beatles: Get Back,' contributing to an Emmy Award win for sound editing in 2022. Developers building audio separation tools can follow machine learning research like this on daily.dev."}}]} ```