{"id":24687433,"url":"https://github.com/huckiyang/interspeech23-tutorial-para-efficient-cross-modal-tutorial","last_synced_at":"2026-01-05T02:04:37.602Z","repository":{"id":188165954,"uuid":"678220400","full_name":"huckiyang/Interspeech23-Tutorial-Para-Efficient-Cross-Modal-Tutorial","owner":"huckiyang","description":"Interspeech Tutorial - Resource Efficient and Cross-Modal Learning Toward Foundation Modeling ","archived":false,"fork":false,"pushed_at":"2023-10-09T09:57:56.000Z","size":49,"stargazers_count":15,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-26T16:19:35.461Z","etag":null,"topics":["lora","nlp","speech-processing","tutorial"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/huckiyang.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-08-14T03:37:04.000Z","updated_at":"2024-06-26T05:50:56.000Z","dependencies_parsed_at":"2023-08-14T04:39:58.970Z","dependency_job_id":null,"html_url":"https://github.com/huckiyang/Interspeech23-Tutorial-Para-Efficient-Cross-Modal-Tutorial","commit_stats":null,"previous_names":["huckiyang/para_efficient_cross_modal_tutorial","huckiyang/interspeech23-tutorial-para-efficient-cross-modal-tutorial"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huckiyang%2FInterspeech23-Tutorial-Para-Efficient-Cross-Modal-Tutorial","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huckiyang%2FInterspeech23-Tutorial-Para-Efficient-Cross-Modal-Tutorial/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huckiyang%2FInterspeech23-Tutorial-Para-Efficient-Cross-Modal-Tutorial/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huckiyang%2FInterspeech23-Tutorial-Para-Efficient-Cross-Modal-Tutorial/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/huckiyang","download_url":"https://codeload.github.com/huckiyang/Interspeech23-Tutorial-Para-Efficient-Cross-Modal-Tutorial/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244874718,"owners_count":20524581,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["lora","nlp","speech-processing","tutorial"],"created_at":"2025-01-26T16:19:36.827Z","updated_at":"2026-01-05T02:04:37.539Z","avatar_url":"https://github.com/huckiyang.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Interspeech 2023 Tutorial\n\n-  Interspeech 23 `Resource Efficient and Cross-Modal Learning Toward Foundation Modeling Tutorial` - [Video](https://www.youtube.com/watch?v=k_egHWj09l4)\n\n- ICASSP 22 Tutorial `Neural Model Reprogramming and Prompting for Speech Modeling` - [Video](https://www.youtube.com/watch?v=-iirkbYkyXI) | [Slide](https://docs.google.com/presentation/d/1sXcxYiTHY_URovr2irb6QvQj7xFIQd1tzObz4SpyEfo/edit) \n- ICASSP 23 Tutorial `Parameter-Efficient Learning (PEL) for Speech and NLP: Adapters, Prompts, and Reprogramming` - [Slide](https://docs.google.com/presentation/d/16ypY73W0xC0WQxkPUtjchxjhzY8XehTEgRSuMJD4QdM/edit?usp=sharing)\n\n## Part 1. Overview of Resource Efficient Learning, Dr. Huck Yang\n\n`9:00`\n\n### 1.1. Parameter-Efficient Learning\n\n- Background of Frozen Model Adaptation\n- Neural Adapter, Reprogramming, Prompting, and Low-Rank Adaptation (LoRA) \n\n| Title | Authors | Code | Year |\n| ----- | ------- | -------- | ---- |\n|[Differentially Private Adapters for Parameter Efficient Acoustic Modeling](https://arxiv.org/abs/2305.11360)|C.-W. Ho et al.|[code](https://github.com/Chun-wei-Ho/)|Interspeech 2023|\n|[Parameter-Efficient Learning for Text-to-Speech Accent Adaptation](https://arxiv.org/abs/2305.11320)|L.-J. Yang et al.|[code](https://tts-research.github.io/)|Interspeech 2023|\n|[A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Model](https://arxiv.org/pdf/2305.11244)|S. Radhakrishnan et al.|[code](https://github.com/Srijith-rkr/KAUST-Whisper-Adapter)|Interspeech 2023|\n\n### 1.2. Memory-Efficient Learning\n\n- Reduce to GPU / TPU Memory During the Training (e.g., the Memory of Activation)\n- Model Serialization\n- Efficient On-Device Learning via Feature Reprogramming (CVPR 2022)\n- Ladder-Side Tuning (NeurIPS 2022)\n\n#### 1.3 How to Estimate which Layer or which Model to Tune?\n\n- Universal Approximation Theory (IEEE TIP 1993)\n- LogME: Practical Assessment of Pre-trained Models for Transfer Learning (ICML 2021)\n- Latent Space Alignment in \"Reprogramming Acoustic Models for Time Series Classification\" (ICML 2021)\n\n| Title | Authors | Code | Year |\n| ----- | ------- | -------- | ---- |\n|[How to Estimate Model Transferability of Pre-Trained Speech Models?](https://arxiv.org/pdf/2306.01015.pdf)|Z.-C. Chen et al.|[code](https://github.com/virginiakm1988/LogME-CTC)|Interspeech 2023|\n\n#### 1.4 Advanced Low-Rank Adaptation (LoRA) Techniques\n\n- Cross-Modal Merging\n- Low-Rank Adaptation (LoRA) for Foundation Modeling and Pre-Training\n\n#### 1.5 Community Service\n\n- Special Session in ICASSP 2024: In-Context Learning for Speech and Language Processing\n- icassp24-icl-sp@googlegroups.com\n\n#### Break: Hand-on Session 1 (5 min)\n\n- How to Train Your Whisper with Neural Adapter and LoRA\n\n\n## Part 2: Trustworthy AI and Cross-Modal Learning in the Era of Foundation Models, Dr. Pin-Yu Chen\n\n`11:00 to 11:45`\n\n## Part 3: Multimodal Pre-Training for Automatic Speech Recognition and Vision Sharing, Dr. Shalini Ghosh\n\n`11:45 to 12:20`\n\n### Spotlight Invited Talk, \"Prompting LLM for ASR,\" by Dr. Chunyang Wu, Meta AI\n\n`12:20 to 12:30`\n\n## QA and Plenary Discussion\n\n`12:40 to 12:45`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuckiyang%2Finterspeech23-tutorial-para-efficient-cross-modal-tutorial","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhuckiyang%2Finterspeech23-tutorial-para-efficient-cross-modal-tutorial","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuckiyang%2Finterspeech23-tutorial-para-efficient-cross-modal-tutorial/lists"}