{"total":26,"rows":[{"id":"2406.10118","title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages","created":"2024-06-14","cited_by_count":43,"area":null},{"id":"2511.01380","title":"Confounding Factors in Relating Model Performance to Morphology","created":"2025-11-03","cited_by_count":14,"area":null},{"id":"2406.09202","title":"Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn't","created":"2024-06-13","cited_by_count":4,"area":null},{"id":"2506.12450","title":"Language Surgery in Multilingual Large Language Models","created":"2025-06-14","cited_by_count":4,"area":null},{"id":"2605.05611","title":"X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2606.18466","title":"Montreal Forced Aligner and the state of speech-to-text alignment in 2026","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2406.05733","title":"MrRank: Improving Question Answering Retrieval System through Multi-Result Ranking Model","created":"2024-06-09","cited_by_count":2,"area":null},{"id":"2410.04795","title":"Representing the Under-Represented: Cultural and Core Capability Benchmarks for Developing Thai Large Language Models","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2410.16221","title":"On Creating an English-Thai Code-switched Machine Translation in Medical Domain","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2507.14664","title":"Mangosteen: An Open Thai Corpus for Language Model Pretraining","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2508.12243","title":"SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?","created":"2025-08-17","cited_by_count":2,"area":null},{"id":"2412.03877","title":"AyutthayaAlpha: A Thai-Latin Script Transliteration Transformer","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2509.18722","title":"LOTUSDIS: A Thai far-field meeting corpus for robust conversational ASR","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2511.21229","title":"Developing an Open Conversational Speech Corpus for the Isan Language","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2602.19174","title":"TurkicNLP: An NLP Toolkit for Turkic Languages","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2609.03502","title":"Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2403.16127","title":"WangchanLion and WangchanX MRC Eval","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2405.07586","title":"Thai Universal Dependency Treebank","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2406.06000","title":"ThaiCoref: Thai Coreference Resolution Dataset","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2411.10083","title":"Xmodel-1.5: An 1B-scale Multilingual LLM","created":"2024-11-15","cited_by_count":0,"area":null},{"id":"2412.01624","title":"Headline-Guided Extractive Summarization for Thai News Articles","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2504.07858","title":"Empowering Global Voices: A Data-Efficient, Phoneme-Tone Adaptive Approach to High-Fidelity Speech Synthesis","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2603.14111","title":"OasisSimp: An Open-source Asian-English Sentence Simplification Dataset","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2608.12814","title":"FastThaiG2P: Lightning-fast Thai Grapheme-to-phoneme Conversion for Voice Agent Pipelines","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.27558","title":"ThaiTrees: Thai Syntactic Dependency Trees Across Domains","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.14980","title":"Single-Sample Decoding of a Two-Layer Sound-Word Canvas Model for Thai Klon Pad","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}