{"url":"/method/local-prior-matching","slug":"local-prior-matching","name":"LPM","full_name":"Local Prior Matching","full_name_withheld":false,"description_markdown":"**Local Prior Matching** is a semi-supervised objective for speech recognition that distills knowledge from a strong prior (e.g. a language model) to provide learning signal to a discriminative model trained on unlabeled speech. The LPM objective minimizes the cross entropy between the local prior and the model distribution, and is minimized when $q\\_{y\\mid{x}} = \\bar{p}\\_{y\\mid{x}}$. Intuitively, LPM encourages the ASR model to assign posterior probabilities proportional to the linguistic probabilities of the proposed hypotheses.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Semi-Supervised Speech Recognition via Local Prior Matching","paper":"/paper/semi-supervised-speech-recognition-via-local","first_author":"Wei-Ning Hsu","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/semi-supervised-speech-recognition-via-local"},"source":{"url":"https://arxiv.org/abs/2002.10336v1","title":"Semi-Supervised Speech Recognition via Local Prior Matching","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Semi-Supervised Learning Methods","url":"/methods/category/semi-supervised-learning-methods","pwc_aliases":[]}],"n_papers_tagged":17,"archive_num_papers":17,"papers_newest_first":[{"paper":null,"title":"In-silico biological discovery with large perturbation models","date":"2025-03-30","arxiv_id":"2503.23535","n_code_links":0,"syntology":null},{"paper":null,"title":"PreMind: Multi-Agent Video Understanding for Advanced Indexing of Presentation-style Videos","date":"2025-02-28","arxiv_id":"2503.00162","n_code_links":0,"syntology":null},{"paper":null,"title":"Locality-aware Fair Scheduling in LLM Serving","date":"2025-01-24","arxiv_id":"2501.14312","n_code_links":0,"syntology":null},{"paper":null,"title":"Design of Fiber-Longitudinal Optical Power Monitor","date":"2024-10-16","arxiv_id":"2410.12602","n_code_links":0,"syntology":null},{"paper":"/paper/2408-02426","title":"Boosting Memory Efficiency in Transfer Learning for High-Resolution Medical Image Classification","date":"2024-08-05","arxiv_id":"2408.02426","n_code_links":1,"syntology":null},{"paper":"/paper/lightviz-autonomous-light-field-surveying-and","title":"LightViz: Autonomous Light-field Surveying and Mapping for Distributed Light Pollution Monitoring","date":"2024-07-31","arxiv_id":"2408.00808","n_code_links":1,"syntology":null},{"paper":null,"title":"Improving Gaussian Splatting with Localized Points Management","date":"2024-06-06","arxiv_id":"2406.04251","n_code_links":0,"syntology":null},{"paper":null,"title":"LeqMod: Adaptable Lesion-Quantification-Consistent Modulation for Deep Learning Low-Count PET Image Denoising","date":"2024-04-27","arxiv_id":"2404.17994","n_code_links":0,"syntology":null},{"paper":"/paper/fpt-fine-grained-prompt-tuning-for-parameter","title":"Fine-grained Prompt Tuning: A Parameter and Memory Efficient Transfer Learning Method for High-resolution Medical Image Classification","date":"2024-03-12","arxiv_id":"2403.07576","n_code_links":1,"syntology":{"ran":6,"of":7,"unverified":1,"pointer_only":7}},{"paper":null,"title":"Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression","date":"2023-11-23","arxiv_id":"2311.13846","n_code_links":0,"syntology":null},{"paper":null,"title":"Grouping Local Process Models","date":"2023-11-06","arxiv_id":"2311.03040","n_code_links":0,"syntology":null},{"paper":null,"title":"Large Process Models: A Vision for Business Process Management in the Age of Generative AI","date":"2023-09-02","arxiv_id":"2309.00900","n_code_links":0,"syntology":null},{"paper":null,"title":"Model Consistency for Mechanical Design: Bridging Lumped and Distributed Parameter Models with A Priori Guarantees","date":"2023-05-11","arxiv_id":"2305.07082","n_code_links":0,"syntology":null},{"paper":null,"title":"A New Method for the High-Precision Assessment of Tumor Changes in Response to Treatment","date":"2022-09-07","arxiv_id":"2209.03116","n_code_links":0,"syntology":null},{"paper":null,"title":"Urban Housing Prices and Migration's Fertility Intentions: Based on the 2018 China Migrants' Dynamic Survey","date":"2021-12-14","arxiv_id":"2112.07273","n_code_links":0,"syntology":null},{"paper":null,"title":"Towards Robust Graph Neural Networks against Label Noise","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-speech-recognition-via-local","title":"Semi-Supervised Speech Recognition via Local Prior Matching","date":"2020-02-24","arxiv_id":"2002.10336","n_code_links":1,"syntology":null}],"papers_shown":17,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/management","name":"Management","papers":2},{"task":"/task/medical-image-classification","name":"Medical Image Classification","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/image-classification","name":"image-classification","papers":2},{"task":"/task/3dgs","name":"3DGS","papers":1},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/experimental-design","name":"Experimental Design","papers":1},{"task":"/task/fairness","name":"Fairness","papers":1},{"task":"/task/image-compression","name":"Image Compression","papers":1},{"task":"/task/image-denoising","name":"Image Denoising","papers":1},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":1},{"task":"/task/large-language-model","name":"Large Language Model","papers":1},{"task":"/task/learning-with-noisy-labels","name":"Learning with noisy labels","papers":1},{"task":"/task/meta-learning","name":"Meta-Learning","papers":1}],"tasks_shown":20,"n_tasks":28,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":2},{"year":"2022","papers":1},{"year":"2023","papers":4},{"year":"2024","papers":6},{"year":"2025","papers":3}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/local-prior-matching"},"syntology_read_at":"2026-09-25T09:33:49+00:00"}