{"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/pam-prompting-audio-language-models-for-audio","title":"PAM: Prompting Audio-Language Models for Audio Quality Assessment","arxiv_id":"2402.00282","date":"2024-02-01","proceeding":null,"authors":["Soham Deshmukh","Dareen Alharthi","Benjamin Elizalde","Hannes Gamper","Mahmoud Al Ismail","Rita Singh","Bhiksha Raj","Huaming Wang"],"abstract":"While audio quality is a key performance metric for various audio processing tasks, including generative modeling, its objective measurement remains a challenge. Audio-Language Models (ALMs) are pre-trained on audio-text pairs that may contain information about audio quality, the presence of artifacts, or noise. Given an audio input and a text prompt related to quality, an ALM can be used to calculate a similarity score between the two. Here, we exploit this capability and introduce PAM, a no-reference metric for assessing audio quality for different audio processing tasks. Contrary to other \"reference-free\" metrics, PAM does not require computing embeddings on a reference dataset nor training a task-specific model on a costly set of human listening scores. We extensively evaluate the reliability of PAM against established metrics and human listening scores on four tasks: text-to-audio (TTA), text-to-music generation (TTM), text-to-speech (TTS), and deep noise suppression (DNS). We perform multiple ablation studies with controlled distortions, in-the-wild setups, and prompt choices. Our evaluation shows that PAM correlates well with existing metrics and human listening scores. These results demonstrate the potential of ALMs for computing a general-purpose audio quality metric.","url_abs":"https://arxiv.org/abs/2402.00282v1","url_pdf":"https://arxiv.org/pdf/2402.00282v1.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":"pam-prompting-audio-language-models-for-audio","repo_url":"https://github.com/soham97/pam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-quality-assessment","task_name":"Audio Quality Assessment"},{"task_slug":"music-generation","task_name":"Music Generation"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-music-generation","task_name":"Text-to-Music Generation"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.00282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00282"}},"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/soham97/pam","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_fixture":3,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":"5337e68cdb46397d","entry":"do_mixup","repo":"soham97/pam","repo_kind":"official","path":"PAM/models/pytorch_utils.py","file_url":"https://github.com/soham97/pam/blob/HEAD/PAM/models/pytorch_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5337e68cdb46397d"}},{"code_sha256_prefix":"3ac6b7d76e8e3584","entry":"drop_path","repo":"soham97/pam","repo_kind":"official","path":"PAM/models/htsat.py","file_url":"https://github.com/soham97/pam/blob/HEAD/PAM/models/htsat.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"code_sha256_prefix":"a8d84ccaebb23a2a","entry":"evaluate_pam","repo":"soham97/pam","repo_kind":"official","path":"pcc.py","file_url":"https://github.com/soham97/pam/blob/HEAD/pcc.py","link_basis":"first_harvest_node","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":"a8d84ccaebb23a2a"}},{"code_sha256_prefix":"bdcac6c19196f655","entry":"interpolate","repo":"soham97/pam","repo_kind":"official","path":"PAM/models/pytorch_utils.py","file_url":"https://github.com/soham97/pam/blob/HEAD/PAM/models/pytorch_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdcac6c19196f655"}},{"code_sha256_prefix":"9e1c1269ab3f61a7","entry":"load_task_dataframe","repo":"soham97/pam","repo_kind":"official","path":"pcc.py","file_url":"https://github.com/soham97/pam/blob/HEAD/pcc.py","link_basis":"first_harvest_node","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":"9e1c1269ab3f61a7"}},{"code_sha256_prefix":"6e703419174005ee","entry":"move_data_to_device","repo":"soham97/pam","repo_kind":"official","path":"PAM/models/pytorch_utils.py","file_url":"https://github.com/soham97/pam/blob/HEAD/PAM/models/pytorch_utils.py","link_basis":"plan_row","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":"6e703419174005ee"}},{"code_sha256_prefix":"605878f6dcef72e9","entry":"trunc_normal_","repo":"soham97/pam","repo_kind":"official","path":"PAM/models/htsat.py","file_url":"https://github.com/soham97/pam/blob/HEAD/PAM/models/htsat.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"605878f6dcef72e9"}},{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"soham97/pam","repo_kind":"official","path":"PAM/models/htsat.py","file_url":"https://github.com/soham97/pam/blob/HEAD/PAM/models/htsat.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"705be5651717fc89","entry":"get_audio_encoder","repo":"soham97/pam","repo_kind":"official","path":"PAM/models/audio.py","file_url":"https://github.com/soham97/pam/blob/HEAD/PAM/models/audio.py","link_basis":"first_harvest_node","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":"705be5651717fc89"}},{"code_sha256_prefix":"2ecc1e3196019a78","entry":"read_config_as_args","repo":"soham97/pam","repo_kind":"official","path":"PAM/models/utils.py","file_url":"https://github.com/soham97/pam/blob/HEAD/PAM/models/utils.py","link_basis":"first_harvest_node","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":"2ecc1e3196019a78"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}