Methods › General › Semi-Supervised Learning Methods › LPM
Local Prior Matching
LPM
Introduced by Wei-Ning Hsu et al. in Semi-Supervised Speech Recognition via Local Prior Matching
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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|x) = p̅_(y|x). Intuitively, LPM encourages the ASR model to assign posterior probabilities proportional to the linguistic probabilities of the proposed hypotheses.
Papers archive 2025-07-28
17 shown of 17, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
In-silico biological discovery with large perturbation models 30 Mar 2025 · 0 repositories · arXiv:2503.23535
-
PreMind: Multi-Agent Video Understanding for Advanced Indexing of Presentation-style Videos 28 Feb 2025 · 0 repositories · arXiv:2503.00162
-
Locality-aware Fair Scheduling in LLM Serving 24 Jan 2025 · 0 repositories · arXiv:2501.14312
-
Design of Fiber-Longitudinal Optical Power Monitor 16 Oct 2024 · 0 repositories · arXiv:2410.12602
-
Boosting Memory Efficiency in Transfer Learning for High-Resolution Medical Image Classification 5 Aug 2024 · 1 repository · arXiv:2408.02426
-
LightViz: Autonomous Light-field Surveying and Mapping for Distributed Light Pollution Monitoring 31 Jul 2024 · 1 repository · arXiv:2408.00808
-
Improving Gaussian Splatting with Localized Points Management 6 Jun 2024 · 0 repositories · arXiv:2406.04251
-
LeqMod: Adaptable Lesion-Quantification-Consistent Modulation for Deep Learning Low-Count PET Image Denoising 27 Apr 2024 · 0 repositories · arXiv:2404.17994
-
Fine-grained Prompt Tuning: A Parameter and Memory Efficient Transfer Learning Method for High-resolution Medical Image Classification 12 Mar 2024 · 1 repository · arXiv:2403.07576Syntology ran 6 of 7 samples · 1 unverified · 7 pointer-only (licence)
-
Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression 23 Nov 2023 · 0 repositories · arXiv:2311.13846
-
Grouping Local Process Models 6 Nov 2023 · 0 repositories · arXiv:2311.03040
-
Large Process Models: A Vision for Business Process Management in the Age of Generative AI 2 Sep 2023 · 0 repositories · arXiv:2309.00900
-
Model Consistency for Mechanical Design: Bridging Lumped and Distributed Parameter Models with A Priori Guarantees 11 May 2023 · 0 repositories · arXiv:2305.07082
-
A New Method for the High-Precision Assessment of Tumor Changes in Response to Treatment 7 Sep 2022 · 0 repositories · arXiv:2209.03116
-
Urban Housing Prices and Migration's Fertility Intentions: Based on the 2018 China Migrants' Dynamic Survey 14 Dec 2021 · 0 repositories · arXiv:2112.07273
-
Towards Robust Graph Neural Networks against Label Noise 1 Jan 2021 · 0 repositories
-
Semi-Supervised Speech Recognition via Local Prior Matching 24 Feb 2020 · 1 repository · arXiv:2002.10336
Tasks archive 2025-07-28
20 shown of 28 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections