{"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/joint-audio-and-speech-understanding","title":"Joint Audio and Speech Understanding","arxiv_id":"2309.14405","date":"2023-09-25","proceeding":null,"authors":["Yuan Gong","Alexander H. Liu","Hongyin Luo","Leonid Karlinsky","James Glass"],"abstract":"Humans are surrounded by audio signals that include both speech and non-speech sounds. The recognition and understanding of speech and non-speech audio events, along with a profound comprehension of the relationship between them, constitute fundamental cognitive capabilities. For the first time, we build a machine learning model, called LTU-AS, that has a conceptually similar universal audio perception and advanced reasoning ability. Specifically, by integrating Whisper as a perception module and LLaMA as a reasoning module, LTU-AS can simultaneously recognize and jointly understand spoken text, speech paralinguistics, and non-speech audio events - almost everything perceivable from audio signals.","url_abs":"https://arxiv.org/abs/2309.14405v3","url_pdf":"https://arxiv.org/pdf/2309.14405v3.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":"joint-audio-and-speech-understanding","repo_url":"https://github.com/YuanGongND/ltu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.14405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14405"}},"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/YuanGongND/ltu","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"6ffe6f976823aa80","entry":"gen_filename","repo":"YuanGongND/ltu","repo_kind":"official","path":"src/ltu_as/extract_whisper_feature.py","file_url":"https://github.com/YuanGongND/ltu/blob/HEAD/src/ltu_as/extract_whisper_feature.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ffe6f976823aa80"}},{"code_sha256_prefix":"d470fb35524ac29f","entry":"gen_filename","repo":"YuanGongND/ltu","repo_kind":"official","path":"src/ltu_as/inference_batch.py","file_url":"https://github.com/YuanGongND/ltu/blob/HEAD/src/ltu_as/inference_batch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d470fb35524ac29f"}},{"code_sha256_prefix":"29959519495675e9","entry":"remove_punctuation_and_lowercase","repo":"YuanGongND/ltu","repo_kind":"official","path":"src/ltu/eval/eval_audiocaps.py","file_url":"https://github.com/YuanGongND/ltu/blob/HEAD/src/ltu/eval/eval_audiocaps.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"29959519495675e9"}},{"code_sha256_prefix":"eaa6f23755f49c80","entry":"remove_thanks_for_watching","repo":"YuanGongND/ltu","repo_kind":"official","path":"src/ltu_as/inference_gradio.py","file_url":"https://github.com/YuanGongND/ltu/blob/HEAD/src/ltu_as/inference_gradio.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eaa6f23755f49c80"}},{"code_sha256_prefix":"021b47147c4cf95b","entry":"trim_string","repo":"YuanGongND/ltu","repo_kind":"official","path":"src/ltu_as/inference_gradio.py","file_url":"https://github.com/YuanGongND/ltu/blob/HEAD/src/ltu_as/inference_gradio.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"021b47147c4cf95b"}},{"code_sha256_prefix":"b5c3b0851878b618","entry":"load_audio","repo":"YuanGongND/ltu","repo_kind":"official","path":"src/ltu_as/inference_batch.py","file_url":"https://github.com/YuanGongND/ltu/blob/HEAD/src/ltu_as/inference_batch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b5c3b0851878b618"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}