{"total":15,"rows":[{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129,"area":null},{"id":"2505.19978","title":"DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2406.14693","title":"Voice Disorder Analysis: a Transformer-based Approach","created":"2024-06-20","cited_by_count":5,"area":null},{"id":"2410.00511","title":"Pre-training with Synthetic Patterns for Audio","created":"2024-10-01","cited_by_count":3,"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":"2510.01889","title":"Small is Sufficient: Reducing the World AI Energy Consumption Through Model Selection","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2505.20050","title":"MVP: Multi-source Voice Pathology detection","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2601.08358","title":"Linear probing enables Ship-Radiated Noise recognition with pretrained audio embeddings","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2502.06664","title":"Evaluation of Deep Audio Representations for Hearables","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2509.26276","title":"Optimizing Speech Language Models for Acoustic Consistency","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.19368","title":"AMAuT: A Flexible and Efficient Multiview Audio Transformer Framework Trained from Scratch","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2601.06329","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2507.17799","title":"A Concept-based approach to Voice Disorder Detection","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2610.14349","title":"Multimodal Co-Generation With Continuous Bitstream Diffusion","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}