{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/investigating-the-effect-of-residual-and","title":"Investigating the effect of residual and highway connections in speech enhancement models","arxiv_id":null,"date":"2018-10-22","proceeding":"NIPS Workshop IRASL 2018","authors":["Anonymous"],"abstract":"  Residual and skip connections play an important role in many current\n  generative models. Although their theoretical and numerical advantages\n  are understood, their role in speech enhancement systems has not been\n  investigated so far. When performing spectral speech enhancement,\n  residual connections are very similar in nature to spectral subtraction,\n  which is the one of the most commonly employed speech enhancement approaches.\n  Highway networks, on the other hand, can be seen as a combination of spectral\n  masking and spectral subtraction. However, when using deep neural networks, such operations would\n  normally happen in a transformed spectral domain, as opposed to traditional speech\n  enhancement where all operations are often done directly on the spectrum.\n  In this paper, we aim to investigate the role of residual and highway\n  connections in deep neural networks for speech enhancement, and verify whether\n  or not they operate similarly to their traditional, digital signal processing\n  counterparts. We visualize the outputs of such connections, projected back to\n  the spectral domain, in models trained for speech denoising, and show that while\n  skip connections do not necessarily improve performance with regards to the\n  number of parameters, they make speech enhancement models more interpretable.","url_abs":"https://openreview.net/forum?id=rkzeXBDos7","url_pdf":"https://openreview.net/pdf?id=rkzeXBDos7","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"investigating-the-effect-of-residual-and","repo_url":"https://github.com/jfsantos/irasl2018","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"speech-denoising","task_name":"Speech Denoising"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[{"method_slug":"highway-networks","method_name":"Highway networks"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"jfsantos/irasl2018","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0f1004a55882b667045027fce0df9cf145a81a656f9314893e4ed059c5821d5d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}