{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/combining-spectral-and-self-supervised","title":"Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation","arxiv_id":"2204.02470","date":"2022-04-05","proceeding":null,"authors":["Dan Berrebbi","Jiatong Shi","Brian Yan","Osbel Lopez-Francisco","Jonathan D. Amith","Shinji Watanabe"],"abstract":"Self-Supervised Learning (SSL) models have been successfully applied in various deep learning-based speech tasks, particularly those with a limited amount of data. However, the quality of SSL representations depends highly on the relatedness between the SSL training domain(s) and the target data domain. On the contrary, spectral feature (SF) extractors such as log Mel-filterbanks are hand-crafted non-learnable components, and could be more robust to domain shifts. The present work examines the assumption that combining non-learnable SF extractors to SSL models is an effective approach to low resource speech tasks. We propose a learnable and interpretable framework to combine SF and SSL representations. The proposed framework outperforms significantly both baseline and SSL models on Automatic Speech Recognition (ASR) and Speech Translation (ST) tasks on three low resource datasets. We additionally design a mixture of experts based combination model. This last model reveals that the relative contribution of SSL models over conventional SF extractors is very small in case of domain mismatch between SSL training set and the target language data.","url_abs":"https://arxiv.org/abs/2204.02470v2","url_pdf":"https://arxiv.org/pdf/2204.02470v2.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":"combining-spectral-and-self-supervised","repo_url":"https://github.com/espnet/espnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.02470","atlas_url":"https://app.syntology.ai/?focus=2204.02470","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2204.02470"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2204.02470\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2204.02470"},"call":"get_concepts_for_paper(arxiv_id=\"2204.02470\")"}],"by_repo":[{"repo":"espnet/espnet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1910.10909","2111.14706","2304.04596","2025.acl-long.135"],"harvested_for_calls":[{"arxiv_id":"1910.10909","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.10909"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.10909\")"},{"arxiv_id":"2111.14706","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2111.14706"},"call":"get_harvested_code_for_paper(arxiv_id=\"2111.14706\")"},{"arxiv_id":"2304.04596","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.04596"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.04596\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b1cf2d25a8d59323ed075d6b2eb6dcfb028ac0b5301ff0c2e455837027bed9b1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}