TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification
Audio-language models (ALMs) excel in zero-shot audio classification, a task where models classify previously unseen audio clips at test time by leveraging descriptive natural language prompts. We introduce TSPE (Task-Specific Prompt Ensemble), a simple, training-free hard prompting method that boosts ALEs' zero-shot performance by customizing prompts for diverse audio classification tasks. Rather than using generic template-based prompts like "Sound of a car" we generate context-rich prompts, such as "Sound of a car coming from a tunnel". Specifically, we leverage label information to identify suitable sound attributes, such as "loud" and "feeble", and appropriate sound sources, such as "tunnel" and "street" and incorporate this information into the prompts used by Audio-Language Models (ALMs) for audio classification. Further, to enhance audio-text alignment, we perform prompt ensemble across TSPE-generated task-specific prompts. When evaluated on 12 diverse audio classification datasets, TSPE improves performance across ALMs by showing an absolute improvement of 1.23-16.36% over vanilla zero-shot evaluation.
Code (0)
등록된 구현이 없습니다.
Tasks
Audio ClassificationClassificationDescriptiveZero-shot Audio ClassificationSimilar Papers 제목 키워드 기반
Insights from the Usage of the Ansible Lightspeed Code Completion Service
The availability of Large Language Models (LLMs) which can generate code, has made it possible to create tools that improve developer productivity. Integrated development environments or IDEs which developers use to writ…
Code CompletionCode GenerationGraph Transformer with Disease Subgraph Positional Encoding for Improved Comorbidity Prediction
Comorbidity, the co-occurrence of multiple medical conditions in a single patient, profoundly impacts disease management and outcomes. Understanding these complex interconnections is crucial, especially in contexts where…
AgentSPEX: An Agent SPecification and EXecution Language
Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reasoning and tool-use steps, leaving control flow and intermediate state…
LLM-based Prompt Ensemble for Reliable Medical Entity Recognition from EHRs
Electronic Health Records (EHRs) are digital records of patient information, often containing unstructured clinical text. Named Entity Recognition (NER) is essential in EHRs for extracting key medical entities like probl…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+1A Knowledge-enhanced Two-stage Generative Framework for Medical Dialogue Information Extraction
This paper focuses on term-status pair extraction from medical dialogues (MD-TSPE), which is essential in diagnosis dialogue systems and the automatic scribe of electronic medical records (EMRs). In the past few years, w…