{"total":20,"rows":[{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"area":null},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2503.08533","title":"ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems","created":"2025-03-11","cited_by_count":7,"area":null},{"id":"2510.01812","title":"SingMOS-Pro: An Comprehensive Benchmark for Singing Quality Assessment","created":"2025-10-02","cited_by_count":7,"area":null},{"id":"2506.01845","title":"On-device Streaming Discrete Speech Units","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2602.05220","title":"Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2506.04518","title":"Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2506.15456","title":"Factorized RVQ-GAN For Disentangled Speech Tokenization","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2508.11224","title":"Benchmarking Prosody Encoding in Discrete Speech Tokens","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2512.17209","title":"Do Foundational Audio Encoders Understand Music Structure?","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2601.12205","title":"Do Neural Codecs Generalize? A Controlled Study Across Unseen Languages and Non-Speech Tasks","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2507.12701","title":"Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2603.13952","title":"LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2606.19951","title":"Investigating Human-Model Discrepancies in Speech Quality Assessment via Acoustic and Prosodic Perturbations","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.20137","title":"PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.26350","title":"Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.17509","title":"LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.23951","title":"HaikuS2S: A Cascaded System For Responding In Verse","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.29448","title":"YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.00154","title":"How Robust Are Neural Audio Codecs for African Speech? A Multi-Task Benchmark and the Limits of Perceptual Quality","created":"2026-09-10","cited_by_count":0,"area":null}],"next_cursor":null}