International Conference on Natural Language and Speech Processing 2025: all accepted papers
- A Retail-Corpus for Aspect-Based Sentiment Analysis with Large Language Models ↗Oleg Silcenco, Marcos Machado, Wallace Ugulino et al.
- ASR Models for Traditional Emirati Arabic: Challenges, Adaptations, and Performance EvaluationMaha Alblooki, Kentaro Inui, Shady Shehataour summary
- Adapting ASR Models for Speech-to-Punctuated-Text Recognition with Utterance Gluing ↗Agata Jakubiak, Piotr Stachyra, Piotr Czubowski et al.
- Assessing ASR Robustness for Burmese: Impacts of Missing Speech Segments and Interruptions ↗Ankit Maurya, Manikandan Ravikiran, Rohit Saluja
- Beyond Labeled Datasets: Advancing TTS with Direct Preference Optimization on Unlabeled Speech Dataset ↗Andrii Zhuravlov, Volodymyr Sydorskyi
- Beyond Shallow Heuristics: Leveraging Human Intuition for Curriculum Learning ↗Vanessa Toborek, Sebastian Müller, Tim Selbach et al.
- Beyond the Boundaries of Research Fields - Mapping Educational Science in the Broader Academic Discourse about Artifical Intelligence ↗Martin Rehm, Zhiru Sun, Maxime Holmberg Sainte-Marie
- Building an Ewe Language Dataset: Towards Enhancing Automatic Speech Recognition Technologies for Low Resource Languages ↗Isaac Wiafe, Akon Obu Ekpezu, Raynard Dodzi Helegah et al.
- CLEAR: Code-Mixed ASR with LLM-Driven Rescoring ↗Shivam Kumar, Md Shad Akhtar
- CMC-SC: Cross-Modal Contextualized ASR Spelling Correction via BERT and WavLM using a Soft Fusion Framework ↗Mohammad Reza Peyghan, Sajjad Amini, Shahrokh Ghaemmaghami
- CUPE: Contextless Universal Phoneme Encoder for Language-Agnostic Speech Processing ↗Abdul Rehman, Jian-jun Zhang, Xiasong Yang
- Cross-Lingual Sentence-Level Skill Identification in English and Danish Job Advertisements ↗Nurlan Musazade, Mike Zhang, József Mezei
- Demographics and Democracy: Benchmarking LLMs' Gender Bias and Political Leaning in European Parliament ↗Jinrui Yang, Xudong Han, Timothy Baldwin
- Domain adaptation and question-answer pooling for Aphasia modelling ↗Uwe Reichel, Monica Gonzalez Machorro, Lisa Maria Ehlen et al.
- Dora explores Clinically Relevant Information in EHRs using NER ↗Martin Laursen, Lina Elkjær Pedersen, Josefine Bak H. Adelhelm et al.
- Efficient Continual Learning for Small Language Models with a Discrete Key-Value Bottleneck ↗Andor Diera, Lukas Galke, Fabian Karl et al.
- Enhancing Arabic Retrieval Augmented Generation through Language Processing ↗Shadi Saleh, Belkacem EL Jattari, Layth Oud et al.
- Evaluating ASR in a Clinical Context : What Whisper Misses ↗Haeeul Hwang, Eric Jordan, Deok-Hee Kim-Dufor et al.
- FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain ↗Anum Afzal, Juraj Vladika, Florian Matthes
- From Context to Emotion: Leveraging LLMs for Recognizing Implicit Emotions ↗Hanane Boutouta, Abdelaziz Lakhfif, Ferial Senator et al.
- From Outliers to Topics in Language Models: Anticipating Trends in News Corpora ↗Evangelia Zve, Benjamin Icard, Alice Breton et al.
- From Performance to Process: Temporal Information Dynamics in Language Model Fine-tuning ↗Frida Hæstrup, Ross Deans Kristensen-McLachlan
- GUIDE: A Framework for Improving Functional Software Test Descriptions with Language Models ↗Mathis Ronzon, Thierry Roger, Zoltan Miklos et al.
- HiSlang-4.9k: A Benchmark Dataset for Hindi Slang Detection and Identification ↗Tanmay Tiwari, Vibhu Gupta, Manikandan Ravikiran et al.
- Improving French Synthetic Speech Quality via SSML Prosody Control ↗Nassima Ould Ouali, Awais Hussain Sani, Ruben Bueno et al.
- L1RA: Dynamic Rank Assignment in LoRA Fine-Tuning ↗Raul Singh, Nicolò Brunello, Vincenzo Scotti et al.
- Next Speaker Prediction for Multi-Speaker Dialogue with Large Language Models ↗Lukas Hilgert, Jan Niehues
- On Limitations of LLM as Annotator for Low Resource Languages ↗Suramya Jadhav, Abhay Shanbhag, Amogh Thakurdesai et al.
- Re-Representation in Sentential Relation Extraction with Sequence Routing Algorithm ↗Ramazan Bahrami, Ramin Yahyapour
- Scalable Text Vectorization with Hyperdimensional Computing Through Selective Word Encoding ↗Timur Mudarisov, Evgeny Polyachenko, Zsofia Kraussl et al.
- Signals from Academic Hiring: A Decade of Skill Demands at a Danish University ↗Zhiru Sun, Jakob Mørup Wang
- Speech-Based Depressive Mood Detection in the Presence of Multiple Sclerosis: A Cross-Corpus and Cross-Lingual Study ↗Monica Gonzalez Machorro, Uwe Reichel, Pascal Hecker et al.
- Style-Controlled Response Generation for Dialog Systems with Intimacy Interpretation ↗Takuto Miura, Kiyoaki Shirai, Natthawut Kertkeidkachorn
- Tachelhiyt-Darija: a parallel speech corpus for two underrepresented languagesNoureddine Atouf, Elsayed Issa, Said Ouzbayrour summary
- The Chunking Paradigm: Recursive Semantic for RAG Optimization ↗Seemab Latif, Huma Ameer, Muhammad Hannan Akram et al.
- The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum ↗Olufunke O. Sarumi, Charles Welch, Daniel Braun et al.
- The Need for Robust and Inclusive Benchmarks in Evaluating LLMs on Arabic Text ↗Lubana Al Rayes, Ashraf Elnagar
- Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5 ↗Thao Anh Dang, Limor Raviv, Lukas Galke
- Towards Robust Urdu Aspect-based Sentiment Analysis through Weakly-Supervised Annotation Framework ↗Zoya Maqsood, Seemab Latif, Rabia Latif
- Word-level Language Identification using Encoder-Only and Decoder-Only Models ↗Javier Iranzo-Sánchez, Parnia Bahar, Alejandro Pérez-González-de-Martos et al.
- Zero-Shot Commonsense Validation and Reasoning with Large Language Models: An Evaluation on SemEval-2020 Task 4 Dataset ↗Rawand Alfugaha, Mohammad AL-Smadi
- topicwizard - a Modern, Model-agnostic Framework for Topic Model Visualization and Interpretation ↗Márton Kardos, Kenneth Enevoldsen, Kristoffer Nielbo
This page in Markdown → https://md.research.elamur.ai/free/en/venues/icnlsp/2025/papers/