Matches in SemOpenAlex for { <https://semopenalex.org/work/W4223978050> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4223978050 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" @default.
- W4223978050 created "2022-04-19" @default.
- W4223978050 creator A5004778663 @default.
- W4223978050 creator A5022802322 @default.
- W4223978050 creator A5022943029 @default.
- W4223978050 creator A5030425371 @default.
- W4223978050 creator A5049575288 @default.
- W4223978050 creator A5061492058 @default.
- W4223978050 date "2022-03-29" @default.
- W4223978050 modified "2023-09-29" @default.
- W4223978050 title "WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models" @default.
- W4223978050 doi "https://doi.org/10.48550/arxiv.2203.15863" @default.
- W4223978050 hasPublicationYear "2022" @default.
- W4223978050 type Work @default.
- W4223978050 citedByCount "0" @default.
- W4223978050 crossrefType "posted-content" @default.
- W4223978050 hasAuthorship W4223978050A5004778663 @default.
- W4223978050 hasAuthorship W4223978050A5022802322 @default.
- W4223978050 hasAuthorship W4223978050A5022943029 @default.
- W4223978050 hasAuthorship W4223978050A5030425371 @default.
- W4223978050 hasAuthorship W4223978050A5049575288 @default.
- W4223978050 hasAuthorship W4223978050A5061492058 @default.
- W4223978050 hasBestOaLocation W42239780501 @default.
- W4223978050 hasConcept C104317684 @default.
- W4223978050 hasConcept C111919701 @default.
- W4223978050 hasConcept C118505674 @default.
- W4223978050 hasConcept C125411270 @default.
- W4223978050 hasConcept C137293760 @default.
- W4223978050 hasConcept C154945302 @default.
- W4223978050 hasConcept C177264268 @default.
- W4223978050 hasConcept C178790620 @default.
- W4223978050 hasConcept C185592680 @default.
- W4223978050 hasConcept C195324797 @default.
- W4223978050 hasConcept C199360897 @default.
- W4223978050 hasConcept C204321447 @default.
- W4223978050 hasConcept C2776230583 @default.
- W4223978050 hasConcept C2776760102 @default.
- W4223978050 hasConcept C2778344882 @default.
- W4223978050 hasConcept C2779439875 @default.
- W4223978050 hasConcept C28490314 @default.
- W4223978050 hasConcept C41008148 @default.
- W4223978050 hasConcept C55493867 @default.
- W4223978050 hasConcept C66746571 @default.
- W4223978050 hasConceptScore W4223978050C104317684 @default.
- W4223978050 hasConceptScore W4223978050C111919701 @default.
- W4223978050 hasConceptScore W4223978050C118505674 @default.
- W4223978050 hasConceptScore W4223978050C125411270 @default.
- W4223978050 hasConceptScore W4223978050C137293760 @default.
- W4223978050 hasConceptScore W4223978050C154945302 @default.
- W4223978050 hasConceptScore W4223978050C177264268 @default.
- W4223978050 hasConceptScore W4223978050C178790620 @default.
- W4223978050 hasConceptScore W4223978050C185592680 @default.
- W4223978050 hasConceptScore W4223978050C195324797 @default.
- W4223978050 hasConceptScore W4223978050C199360897 @default.
- W4223978050 hasConceptScore W4223978050C204321447 @default.
- W4223978050 hasConceptScore W4223978050C2776230583 @default.
- W4223978050 hasConceptScore W4223978050C2776760102 @default.
- W4223978050 hasConceptScore W4223978050C2778344882 @default.
- W4223978050 hasConceptScore W4223978050C2779439875 @default.
- W4223978050 hasConceptScore W4223978050C28490314 @default.
- W4223978050 hasConceptScore W4223978050C41008148 @default.
- W4223978050 hasConceptScore W4223978050C55493867 @default.
- W4223978050 hasConceptScore W4223978050C66746571 @default.
- W4223978050 hasLocation W42239780501 @default.
- W4223978050 hasOpenAccess W4223978050 @default.
- W4223978050 hasPrimaryLocation W42239780501 @default.
- W4223978050 hasRelatedWork W1542956019 @default.
- W4223978050 hasRelatedWork W1995170466 @default.
- W4223978050 hasRelatedWork W2039387658 @default.
- W4223978050 hasRelatedWork W2063568087 @default.
- W4223978050 hasRelatedWork W2547835662 @default.
- W4223978050 hasRelatedWork W3006901707 @default.
- W4223978050 hasRelatedWork W3107474891 @default.
- W4223978050 hasRelatedWork W3192727970 @default.
- W4223978050 hasRelatedWork W4224919006 @default.
- W4223978050 hasRelatedWork W4310408674 @default.
- W4223978050 isParatext "false" @default.
- W4223978050 isRetracted "false" @default.
- W4223978050 workType "article" @default.