English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Speech representations learned from Self-supervised learning (SSL) models canbenefit various speech processing tasks. However, utilizing SSL representationsusually requires fine-tuning the pre-trained models or designing task-specificdownstream models and loss functions, causing much memory usage and humanlabor. Recently, prompting in Natural Language Processing (NLP) has been foundto be an efficient technique to leverage pre-trained language models (LMs).Specifically, prompt tuning optimizes a limited number of task-specificparameters with a fixed pre-trained model; as a result, only a small set ofparameters is needed to be stored for each task. Prompt tuning improvescomputation and memory efficiency by leveraging the pre-trained LM's predictionability. Nevertheless, such a paradigm is little studied in the speechcommunity. We report in this paper the first exploration of the prompt tuningparadigm for speech processing tasks based on Generative Spoken Language Model(GSLM). Experiment results show that the prompt tuning technique achievescompetitive performance in speech classification tasks with fewer trainableparameters than fine-tuning specialized downstream models. We further study thetechnique in challenging sequence generation tasks. Prompt tuning alsodemonstrates its potential, while the limitation and possible researchdirections are discussed in this paper. The source code is available onhttps://github.com/ga642381/SpeechPrompt.

SpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks