The detection of hate speech in social media platforms is very crucial these days. This is due to its adverse impact on mental health, social harmony, and online safety. This paper presents the overview of the shared task on Multimodal Hate Speech Detection in Dravidian Languages organized as part of DravidianLangTech@NAACL 2025. The task emphasizes detecting hate speech in social media content that combines speech and text. Here, we focus on three low-resource Dravidian languages: Malayalam, Tamil, and Telugu. Participants were required to classify hate speech in three sub-tasks, each corresponding to one of these languages. The dataset was curated by collecting speech and corresponding text from YouTube videos. Various machine learning and deep learning-based models, including transformer-based architectures and multimodal frameworks, were employed by the participants. The submissions were evaluated using the macro F1 score. Experimental results underline the potential of multimodal approaches in advancing hate speech detection for low-resource languages. Team SSNTrio achieved the highest F1 score in Malayalam and Tamil of 0.7511 and 0.7332, respectively. Team lowes scored the best F1 score of 0.3817 in the Telugu sub-task.

This research presents an improved Tamil Automatic Speech Recognition (ASR) system designed to enhance accessibility for elderly and transgender populations by addressing unique language challenges. We address the challenges of Tamil ASR—including limited high-quality curated datasets, unique phonetic characteristics, and word-merging tendencies—through a comprehensive pipeline. Our methodology integrates Adaptive Variational Mode Decomposition (AVMD) for selective noise reduction based on signal characteristics, Silero Voice Activity Detection (VAD) with GRU architecture to eliminate non-speech segments, and fine-tuning of OpenAI’s Whisper model optimized for Tamil transcription. The system employs beam search decoding during inference to further improve accuracy. Our approach achieved state-of-the-art performance with a Word Error Rate (WER) of 31.9,winning first place in the LT-EDI 2025 shared task.

Automatic Speech Recognition (ASR) technology can potentially make marginalized communities more accessible. However, older adultsand transgender speakers are usually highly disadvantaged in accessing valuable services due to low digital literacy and social biases. In Tamil-speaking regions, these are further compounded by the inability of ASR models to address their unique speech types, accents, and spontaneous speaking styles. To bridge this gap, the LT-EDI-2025 shared task is designed to develop robust ASR systems for Tamil speech from vulnerable populations. Using whisper based models, this task is designed to improve recognition rates in speech data collected from older adults and transgender speakers in naturalistic settings such as banks, hospitals and public offices. By bridging the linguistic heterogeneity and acoustic variability among this underrepresented population, the shared task is designed to develop inclusive AI solutions that break communication barriers and empower vulnerable populations in Tamil Nadu.

This paper summarizes the shared task on multimodal abusive language detection and sentiment analysis in Dravidian languages as part of the third Workshop on Speech and Language Technologies for Dravidian Languages at RANLP 2023. This shared task provides a platform for researchers worldwide to submit their models on two crucial social media data analysis problems in Dravidian languages - abusive language detection and sentiment analysis. Abusive language detection identifies social media content with abusive information, whereas sentiment analysis refers to the problem of determining the sentiments expressed in a text. This task aims to build models for detecting abusive content and analyzing fine-grained sentiment from multimodal data in Tamil and Malayalam. The multimodal data consists of three modalities - video, audio and text. The datasets for both tasks were prepared by collecting videos from YouTube. Sixty teams participated in both tasks. However, only two teams submitted their results. The submissions were evaluated using macro F1-score.