{"total":18,"rows":[{"id":"2602.07143","title":"Massive Sound Embedding Benchmark (MSEB)","created":"2026-02-06","cited_by_count":9,"area":null},{"id":"2409.06372","title":"SpeechTaxi: On Multilingual Semantic Speech Classification","created":"2024-09-10","cited_by_count":6,"area":null},{"id":"2509.12093","title":"SENSE models: an open source solution for multilingual and multimodal semantic-based tasks","created":"2025-09-15","cited_by_count":6,"area":null},{"id":"2509.15389","title":"Exploring Fine-Tuning of Large Audio Language Models for Spoken Language Understanding under Limited Speech Data","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2501.02370","title":"Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison","created":"2025-01-04","cited_by_count":5,"area":null},{"id":"2505.20163","title":"Exploring Generative Error Correction for Dysarthric Speech Recognition","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2510.07890","title":"Standard-to-Dialect Transfer Trends Differ across Text and Speech: A Case Study on Intent and Topic Classification in German Dialects","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2606.08194","title":"GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models","created":"2026-06-06","cited_by_count":2,"area":null},{"id":"2412.11978","title":"Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2603.21478","title":"TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2605.09167","title":"WorldSpeech: A Multilingual Speech Corpus from Around the World","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2608.18689","title":"Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2505.20176","title":"\"KAN you hear me?\" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2603.21940","title":"SLURP-TN : Resource for Tunisian Dialect Spoken Language Understanding","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2605.04556","title":"Benchmarking LLMs on the Massive Sound Embedding Benchmark (MSEB)","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.25444","title":"Does Translation-Enhanced Speech Encoder Pre-training Affect Speech LLMs?","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2609.27086","title":"NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.35820","title":"$\\tau$-Multilingual: Benchmarking Voice Agents Across Languages","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}