{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/a-fully-convolutional-neural-network-for","title":"A Fully Convolutional Neural Network for Speech Enhancement","arxiv_id":"1609.07132","date":"2016-09-22","proceeding":null,"authors":["Se Rim Park","Jinwon Lee"],"abstract":"In hearing aids, the presence of babble noise degrades hearing\nintelligibility of human speech greatly. However, removing the babble without\ncreating artifacts in human speech is a challenging task in a low SNR\nenvironment. Here, we sought to solve the problem by finding a `mapping'\nbetween noisy speech spectra and clean speech spectra via supervised learning.\nSpecifically, we propose using fully Convolutional Neural Networks, which\nconsist of lesser number of parameters than fully connected networks. The\nproposed network, Redundant Convolutional Encoder Decoder (R-CED), demonstrates\nthat a convolutional network can be 12 times smaller than a recurrent network\nand yet achieves better performance, which shows its applicability for an\nembedded system: the hearing aids.","url_abs":"http://arxiv.org/abs/1609.07132v1","url_pdf":"http://arxiv.org/pdf/1609.07132v1.pdf","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":"a-fully-convolutional-neural-network-for","repo_url":"https://github.com/AlberetOZ/MIL_test_noise","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-fully-convolutional-neural-network-for","repo_url":"https://github.com/RArbore/Deep-Learning-Hearing-Aid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-fully-convolutional-neural-network-for","repo_url":"https://github.com/achaitu/SpeechDenoisingDNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"a-fully-convolutional-neural-network-for","repo_url":"https://github.com/ahmetcanaydemir/sekte","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-fully-convolutional-neural-network-for","repo_url":"https://github.com/rdadlaney/Audio-Denoiser-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-fully-convolutional-neural-network-for","repo_url":"https://github.com/zhr1201/CNN-for-single-channel-speech-enhancement","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.07132","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}