{"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/can-synthetic-audio-from-generative","title":"Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?","arxiv_id":"2406.08800","date":"2024-06-13","proceeding":null,"authors":["Tiantian Feng","Dimitrios Dimitriadis","Shrikanth Narayanan"],"abstract":"Recent advances in foundation models have enabled audio-generative models that produce high-fidelity sounds associated with music, events, and human actions. Despite the success achieved in modern audio-generative models, the conventional approach to assessing the quality of the audio generation relies heavily on distance metrics like Frechet Audio Distance. In contrast, we aim to evaluate the quality of audio generation by examining the effectiveness of using them as training data. Specifically, we conduct studies to explore the use of synthetic audio for audio recognition. Moreover, we investigate whether synthetic audio can serve as a resource for data augmentation in speech-related modeling. Our comprehensive experiments demonstrate the potential of using synthetic audio for audio recognition and speech-related modeling. Our code is available at https://github.com/usc-sail/SynthAudio.","url_abs":"https://arxiv.org/abs/2406.08800v2","url_pdf":"https://arxiv.org/pdf/2406.08800v2.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":"can-synthetic-audio-from-generative","repo_url":"https://github.com/usc-sail/synthaudio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.08800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08800"}},"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/usc-sail/synthaudio","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"0b3795f9775ce118","entry":"checkpoint_filter_fn","repo":"usc-sail/synthaudio","repo_kind":"official","path":"src/models/vision_transformer.py","file_url":"https://github.com/usc-sail/synthaudio/blob/HEAD/src/models/vision_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b3795f9775ce118"}},{"code_sha256_prefix":"94eb8473e293f06f","entry":"collate_fn","repo":"usc-sail/synthaudio","repo_kind":"official","path":"src/dataloader/dataloader.py","file_url":"https://github.com/usc-sail/synthaudio/blob/HEAD/src/dataloader/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"94eb8473e293f06f"}},{"code_sha256_prefix":"ced6bc2bfdfe0059","entry":"get_sinusoid_encoding","repo":"usc-sail/synthaudio","repo_kind":"official","path":"src/models/ast_models.py","file_url":"https://github.com/usc-sail/synthaudio/blob/HEAD/src/models/ast_models.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ced6bc2bfdfe0059"}},{"code_sha256_prefix":"8ec895eaa3183a6c","entry":"padding_cropping","repo":"usc-sail/synthaudio","repo_kind":"official","path":"src/dataloader/dataloader.py","file_url":"https://github.com/usc-sail/synthaudio/blob/HEAD/src/dataloader/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ec895eaa3183a6c"}},{"code_sha256_prefix":"818f33a090227b85","entry":"preemphasis","repo":"usc-sail/synthaudio","repo_kind":"official","path":"src/dataloader/dataloader.py","file_url":"https://github.com/usc-sail/synthaudio/blob/HEAD/src/dataloader/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"818f33a090227b85"}},{"code_sha256_prefix":"e2f4827b035ebd30","entry":"prepare_mask","repo":"usc-sail/synthaudio","repo_kind":"official","path":"src/models/whisper.py","file_url":"https://github.com/usc-sail/synthaudio/blob/HEAD/src/models/whisper.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e2f4827b035ebd30"}},{"code_sha256_prefix":"109c74bc1997c975","entry":"resize_pos_embed","repo":"usc-sail/synthaudio","repo_kind":"official","path":"src/models/vision_transformer.py","file_url":"https://github.com/usc-sail/synthaudio/blob/HEAD/src/models/vision_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"109c74bc1997c975"}},{"code_sha256_prefix":"fac6d3517cd4d773","entry":"mel_filters","repo":"usc-sail/synthaudio","repo_kind":"official","path":"src/models/whisper.py","file_url":"https://github.com/usc-sail/synthaudio/blob/HEAD/src/models/whisper.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fac6d3517cd4d773"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}