{"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/benchmarking-children-s-asr-with-supervised","title":"Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models","arxiv_id":"2406.10507","date":"2024-06-15","proceeding":null,"authors":["Ruchao Fan","Natarajan Balaji Shankar","Abeer Alwan"],"abstract":"Speech foundation models (SFMs) have achieved state-of-the-art results for various speech tasks in supervised (e.g. Whisper) or self-supervised systems (e.g. WavLM). However, the performance of SFMs for child ASR has not been systematically studied. In addition, there is no benchmark for child ASR with standard evaluations, making the comparisons of novel ideas difficult. In this paper, we initiate and present a comprehensive benchmark on several child speech databases based on various SFMs (Whisper, Wav2vec2.0, HuBERT, and WavLM). Moreover, we investigate finetuning strategies by comparing various data augmentation and parameter-efficient finetuning (PEFT) methods. We observe that the behaviors of these methods are different when the model size increases. For example, PEFT matches the performance of full finetuning for large models but worse for small models. To stabilize finetuning using augmented data, we propose a perturbation invariant finetuning (PIF) loss as a regularization.","url_abs":"https://arxiv.org/abs/2406.10507v1","url_pdf":"https://arxiv.org/pdf/2406.10507v1.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":"benchmarking-children-s-asr-with-supervised","repo_url":"https://github.com/Diamondfan/SPAPL_KidsASR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.10507","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10507"}},"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/Diamondfan/SPAPL_KidsASR","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"e6d1df98e12bc2c6","entry":"create_vocabulary_from_data","repo":"Diamondfan/SPAPL_KidsASR","repo_kind":"official","path":"src/bin/train_asr_ctc.py","file_url":"https://github.com/Diamondfan/SPAPL_KidsASR/blob/HEAD/src/bin/train_asr_ctc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e6d1df98e12bc2c6"}},{"code_sha256_prefix":"82ef3d11f05bc76d","entry":"list_field","repo":"Diamondfan/SPAPL_KidsASR","repo_kind":"official","path":"src/ctc_arguments.py","file_url":"https://github.com/Diamondfan/SPAPL_KidsASR/blob/HEAD/src/ctc_arguments.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"82ef3d11f05bc76d"}},{"code_sha256_prefix":"43a4ff32e4c5d744","entry":"load_data","repo":"Diamondfan/SPAPL_KidsASR","repo_kind":"official","path":"src/bin/transcribe.py","file_url":"https://github.com/Diamondfan/SPAPL_KidsASR/blob/HEAD/src/bin/transcribe.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"43a4ff32e4c5d744"}},{"code_sha256_prefix":"cfb09657fff12fcf","entry":"shift_tokens_right","repo":"Diamondfan/SPAPL_KidsASR","repo_kind":"official","path":"src/models/modeling_whisper.py","file_url":"https://github.com/Diamondfan/SPAPL_KidsASR/blob/HEAD/src/models/modeling_whisper.py","link_basis":"plan_row","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":"cfb09657fff12fcf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}