{"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/phase-aware-speech-enhancement-with-deep-1","title":"Phase-aware Speech Enhancement with Deep Complex U-Net","arxiv_id":"1903.03107","date":"2019-03-07","proceeding":"ICLR 2019 5","authors":["Hyeong-Seok Choi","Jang-Hyun Kim","Jaesung Huh","Adrian Kim","Jung-Woo Ha","Kyogu Lee"],"abstract":"Most deep learning-based models for speech enhancement have mainly focused on\nestimating the magnitude of spectrogram while reusing the phase from noisy\nspeech for reconstruction. This is due to the difficulty of estimating the\nphase of clean speech. To improve speech enhancement performance, we tackle the\nphase estimation problem in three ways. First, we propose Deep Complex U-Net,\nan advanced U-Net structured model incorporating well-defined complex-valued\nbuilding blocks to deal with complex-valued spectrograms. Second, we propose a\npolar coordinate-wise complex-valued masking method to reflect the distribution\nof complex ideal ratio masks. Third, we define a novel loss function, weighted\nsource-to-distortion ratio (wSDR) loss, which is designed to directly correlate\nwith a quantitative evaluation measure. Our model was evaluated on a mixture of\nthe Voice Bank corpus and DEMAND database, which has been widely used by many\ndeep learning models for speech enhancement. Ablation experiments were\nconducted on the mixed dataset showing that all three proposed approaches are\nempirically valid. Experimental results show that the proposed method achieves\nstate-of-the-art performance in all metrics, outperforming previous approaches\nby a large margin.","url_abs":"http://arxiv.org/abs/1903.03107v2","url_pdf":"http://arxiv.org/pdf/1903.03107v2.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":"phase-aware-speech-enhancement-with-deep-1","repo_url":"https://github.com/AppleHolic/source_separation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"phase-aware-speech-enhancement-with-deep-1","repo_url":"https://github.com/Doyosae/Phase_aware_Deep_Complex_UNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"phase-aware-speech-enhancement-with-deep-1","repo_url":"https://github.com/saurjya/asteroid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"phase-aware-speech-enhancement-with-deep-1","repo_url":"https://github.com/tarit21/Speech-Enhancement-module","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"phase-aware-speech-enhancement-with-deep-1","repo_url":"https://github.com/ContigoAI/tf1-phase-aware-speech-enhancement","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"phase-aware-speech-enhancement-with-deep-1","repo_url":"https://github.com/IMLHF/SE_DCUNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"phase-aware-speech-enhancement-with-deep-1","repo_url":"https://github.com/chanil1218/DCUnet.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"phase-aware-speech-enhancement-with-deep-1","repo_url":"https://github.com/pheepa/DCUnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"phase-aware-speech-enhancement-with-deep-1","repo_url":"https://github.com/sweetcocoa/DeepComplexUNetPyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.03107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.03107"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ContigoAI/tf1-phase-aware-speech-enhancement","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chanil1218/DCUnet.pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tarit21/Speech-Enhancement-module","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IMLHF/SE_DCUNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AppleHolic/source_separation","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sweetcocoa/DeepComplexUNetPyTorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pheepa/DCUnet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/saurjya/asteroid","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Doyosae/Phase_aware_Deep_Complex_UNet","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"unverified":7},"by_repo_kind":{"listed":{"samples":10,"ran":3,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"51034dda9909e1ac","entry":"pad2d_as","repo":"chanil1218/DCUnet.pytorch","repo_kind":"listed","path":"models/unet.py","file_url":"https://github.com/chanil1218/DCUnet.pytorch/blob/HEAD/models/unet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"51034dda9909e1ac"}},{"code_sha256_prefix":"4f34a2bb82c820d6","entry":"padded_cat","repo":"chanil1218/DCUnet.pytorch","repo_kind":"listed","path":"models/unet.py","file_url":"https://github.com/chanil1218/DCUnet.pytorch/blob/HEAD/models/unet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4f34a2bb82c820d6"}},{"code_sha256_prefix":"38bc458f2cf9c0c8","entry":"unet","repo":"tarit21/Speech-Enhancement-module","repo_kind":"listed","path":"model_unet.py","file_url":"https://github.com/tarit21/Speech-Enhancement-module/blob/HEAD/model_unet.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"none","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38bc458f2cf9c0c8"}},{"code_sha256_prefix":"f95e782ba6f40038","entry":"audio_to_audio_frame_stack","repo":"tarit21/Speech-Enhancement-module","repo_kind":"listed","path":"data_tools.py","file_url":"https://github.com/tarit21/Speech-Enhancement-module/blob/HEAD/data_tools.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f95e782ba6f40038"}},{"code_sha256_prefix":"6357ed97e1c53e22","entry":"blend_noise_randomly","repo":"tarit21/Speech-Enhancement-module","repo_kind":"listed","path":"data_tools.py","file_url":"https://github.com/tarit21/Speech-Enhancement-module/blob/HEAD/data_tools.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6357ed97e1c53e22"}},{"code_sha256_prefix":"c282d206dc6926b1","entry":"config_dataset","repo":"ContigoAI/tf1-phase-aware-speech-enhancement","repo_kind":"listed","path":"code/utils.py","file_url":"https://github.com/ContigoAI/tf1-phase-aware-speech-enhancement/blob/HEAD/code/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c282d206dc6926b1"}},{"code_sha256_prefix":"5130da4b8a3635f7","entry":"get_wav_files","repo":"ContigoAI/tf1-phase-aware-speech-enhancement","repo_kind":"listed","path":"code/utils.py","file_url":"https://github.com/ContigoAI/tf1-phase-aware-speech-enhancement/blob/HEAD/code/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5130da4b8a3635f7"}},{"code_sha256_prefix":"935f962502a3bbb7","entry":"sdr_loss","repo":"ContigoAI/tf1-phase-aware-speech-enhancement","repo_kind":"listed","path":"code/loss.py","file_url":"https://github.com/ContigoAI/tf1-phase-aware-speech-enhancement/blob/HEAD/code/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"935f962502a3bbb7"}},{"code_sha256_prefix":"161a764093492949","entry":"up_depth_concat","repo":"ContigoAI/tf1-phase-aware-speech-enhancement","repo_kind":"listed","path":"code/network.py","file_url":"https://github.com/ContigoAI/tf1-phase-aware-speech-enhancement/blob/HEAD/code/network.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"161a764093492949"}},{"code_sha256_prefix":"5ea6f86366f8b8e0","entry":"weighted_sdr_loss","repo":"ContigoAI/tf1-phase-aware-speech-enhancement","repo_kind":"listed","path":"code/loss.py","file_url":"https://github.com/ContigoAI/tf1-phase-aware-speech-enhancement/blob/HEAD/code/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ea6f86366f8b8e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}