{"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/real-time-target-sound-extraction","title":"Real-Time Target Sound Extraction","arxiv_id":"2211.02250","date":"2022-11-04","proceeding":null,"authors":["Bandhav Veluri","Justin Chan","Malek Itani","Tuochao Chen","Takuya Yoshioka","Shyamnath Gollakota"],"abstract":"We present the first neural network model to achieve real-time and streaming target sound extraction. To accomplish this, we propose Waveformer, an encoder-decoder architecture with a stack of dilated causal convolution layers as the encoder, and a transformer decoder layer as the decoder. This hybrid architecture uses dilated causal convolutions for processing large receptive fields in a computationally efficient manner while also leveraging the generalization performance of transformer-based architectures. Our evaluations show as much as 2.2-3.3 dB improvement in SI-SNRi compared to the prior models for this task while having a 1.2-4x smaller model size and a 1.5-2x lower runtime. We provide code, dataset, and audio samples: https://waveformer.cs.washington.edu/.","url_abs":"https://arxiv.org/abs/2211.02250v3","url_pdf":"https://arxiv.org/pdf/2211.02250v3.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":"real-time-target-sound-extraction","repo_url":"https://github.com/vb000/waveformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"streaming-target-sound-extraction","task_name":"Streaming Target Sound Extraction"},{"task_slug":"target-sound-extraction","task_name":"Target Sound Extraction"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"causal-convolution","method_name":"Causal Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[{"slug":"fsdsoundscapes","name":"FSDSoundScapes","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/streaming-target-sound-extraction-on","task":"Streaming Target Sound Extraction","dataset":"FSDSoundScapes","model":"Waveformer","rank_in_archive_order":1,"of":1,"metrics":{"SI-SNRi":"9.43"},"uses_additional_data":false},{"leaderboard":"/sota/target-sound-extraction-on-fsdsoundscapes","task":"Target Sound Extraction","dataset":"FSDSoundScapes","model":"Waveformer","rank_in_archive_order":1,"of":1,"metrics":{"SI-SNRi":"9.43"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2211.02250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.02250"}},"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/vb000/waveformer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"8e7fce2bb7365742","entry":"load_checkpoint","repo":"vb000/waveformer","repo_kind":"official","path":"src/helpers/utils.py","file_url":"https://github.com/vb000/waveformer/blob/HEAD/src/helpers/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8e7fce2bb7365742"}},{"code_sha256_prefix":"c481103177a670c9","entry":"model_size","repo":"vb000/waveformer","repo_kind":"official","path":"src/helpers/utils.py","file_url":"https://github.com/vb000/waveformer/blob/HEAD/src/helpers/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c481103177a670c9"}},{"code_sha256_prefix":"596dd36d02e6ffdb","entry":"run_time","repo":"vb000/waveformer","repo_kind":"official","path":"src/helpers/utils.py","file_url":"https://github.com/vb000/waveformer/blob/HEAD/src/helpers/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"596dd36d02e6ffdb"}},{"code_sha256_prefix":"f56296e4096f5491","entry":"loss","repo":"vb000/waveformer","repo_kind":"official","path":"src/training/dcc_tf.py","file_url":"https://github.com/vb000/waveformer/blob/HEAD/src/training/dcc_tf.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":"f56296e4096f5491"}},{"code_sha256_prefix":"6f25fb9c4e1a5cb1","entry":"metrics","repo":"vb000/waveformer","repo_kind":"official","path":"src/training/non_causal_dcc_tf.py","file_url":"https://github.com/vb000/waveformer/blob/HEAD/src/training/non_causal_dcc_tf.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":"6f25fb9c4e1a5cb1"}},{"code_sha256_prefix":"dc78050287de1c67","entry":"mod_pad","repo":"vb000/waveformer","repo_kind":"official","path":"src/training/dcc_tf.py","file_url":"https://github.com/vb000/waveformer/blob/HEAD/src/training/dcc_tf.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":"dc78050287de1c67"}},{"code_sha256_prefix":"34831b1d082da07d","entry":"optimizer","repo":"vb000/waveformer","repo_kind":"official","path":"src/training/dcc_tf.py","file_url":"https://github.com/vb000/waveformer/blob/HEAD/src/training/dcc_tf.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":"34831b1d082da07d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}