{"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/wavprompt-towards-few-shot-spoken-language","title":"WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models","arxiv_id":"2203.15863","date":"2022-03-29","proceeding":null,"authors":["Heting Gao","Junrui Ni","Kaizhi Qian","Yang Zhang","Shiyu Chang","Mark Hasegawa-Johnson"],"abstract":"Large-scale auto-regressive language models pretrained on massive text have demonstrated their impressive ability to perform new natural language tasks with only a few text examples, without the need for fine-tuning. Recent studies further show that such a few-shot learning ability can be extended to the text-image setting by training an encoder to encode the images into embeddings functioning like the text embeddings of the language model. Interested in exploring the possibility of transferring the few-shot learning ability to the audio-text setting, we propose a novel speech understanding framework, WavPrompt, where we finetune a wav2vec model to generate a sequence of audio embeddings understood by the language model. We show that WavPrompt is a few-shot learner that can perform speech understanding tasks better than a naive text baseline. We conduct detailed ablation studies on different components and hyperparameters to empirically identify the best model configuration. In addition, we conduct a non-speech understanding experiment to show WavPrompt can extract more information than just the transcriptions. Code is available at https://github.com/Hertin/WavPrompt","url_abs":"https://arxiv.org/abs/2203.15863v2","url_pdf":"https://arxiv.org/pdf/2203.15863v2.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":"wavprompt-towards-few-shot-spoken-language","repo_url":"https://github.com/hertin/wavprompt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"spoken-language-understanding","task_name":"Spoken Language Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.15863","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}