少样本对比适应用于低资源印地语中音频滥用检测
Few-Shot Contrastive Adaptation for Audio Abuse Detection in Low-Resource Indic Languages
AI总结：
本文探讨了CLAP模型在低资源印地语中直接从音频检测滥用语音的可能性，通过ADIMA数据集评估少样本对比适应的效果，发现CLAP能提供强跨语言音频表示，但少样本适应效果语言依赖且非单调。
摘要：
随着社交媒体向语音交互转变，滥用语音检测在多语言和低资源环境下变得越来越重要。当前系统依赖自动语音识别后进行文本仇恨言论分类，但此流程易受转录错误影响且丢失语音的语调信息。本文研究CLAP是否能直接从音频支持滥用语音检测。使用ADIMA数据集，在跨语言和留一语言验证设置下，评估CLAP基于表示的少样本监督对比适应，包含零样本提示作为辅助分析。结果表明，CLAP在十种印地语中产生强跨语言音频表示，轻量级投影仅适应在完全监督系统上训练完整训练数据的性能上具有竞争力。然而，少样本适应的好处是语言依赖性的，并且与样本大小无关单调。这些发现表明，对比音频-文本模型为低资源环境下的跨语言音频滥用检测提供了有希望的基础，同时也表明转移仍存在不完整性和语言特定性。
英文摘要：
Abusive and hateful speech is increasingly spoken rather than written, surfacing in voice notes, calls, and short-form videos. Most detection systems still transcribe speech to text before classifying it, but transcription is unreliable for languages lacking strong speech recognisers, and it discards the tone and emotion that often carry the abuse itself. This paper examines whether abusive speech can instead be detected directly from audio, using CLAP, a model that learns a shared representation of sound and language, evaluated across ten Indic languages in the ADIMA dataset. A lightweight classifier trained on CLAP's existing audio representations, without adapting the model itself, comes within one to three points of a fully supervised system, and far outperforms prompting with no labelled examples at all. Further adaptation with a handful of labelled examples per language yields little extra benefit, varying unpredictably across languages. CLAP-based audio representations thus already offer a strong, inexpensive foundation for detecting abusive speech across languages, lowering the labelled data needed in practice.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
