{"total":33,"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":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"area":null},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"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":"2505.03739","title":"VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model","created":"2025-05-06","cited_by_count":31,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2502.04465","title":"FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks","created":"2025-02-06","cited_by_count":18,"area":null},{"id":"2504.07053","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2025-04-09","cited_by_count":16,"area":null},{"id":"2506.00385","title":"MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2508.02849","title":"SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codec","created":"2025-08-04","cited_by_count":5,"area":null},{"id":"2505.16845","title":"Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2506.22023","title":"Robust and Efficient Autoregressive Speech Synthesis with Dynamic Chunk-wise Prediction Policy","created":"2025-06-27","cited_by_count":4,"area":null},{"id":"2601.17086","title":"SonoEdit: Null-Space Constrained Knowledge Editing for Pronunciation Correction in LLM-Based TTS","created":"2026-01-23","cited_by_count":3,"area":null},{"id":"2509.02244","title":"Spectrogram Patch Codec: A 2D Block-Quantized VQ-VAE and HiFi-GAN for Neural Speech Coding","created":"2025-09-02","cited_by_count":2,"area":null},{"id":"2601.02776","title":"UniSRCodec: Unified and Low-Bitrate Single Codebook Codec with Sub-Band Reconstruction","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2501.05787","title":"MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2506.02414","title":"StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2603.05310","title":"Latent-Mark: An Audio Watermark Robust to Neural Codec Compression","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2605.06765","title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2503.02585","title":"As Good as It KAN Get: High-Fidelity Audio Representation","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2509.24457","title":"Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditions","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2509.25296","title":"Learning Relationships Between Separate Audio Tracks for Creative Applications","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2511.23142","title":"Adapting Neural Audio Codecs to EEG","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2601.20185","title":"Improving X-Codec-2.0 for Multi-Lingual Speech: 25 Hz Latent Rate and 24 kHz Sampling","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2601.20510","title":"Audio Deepfake Detection in the Age of Advanced Text-to-Speech models","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2603.21073","title":"SqueezeComposer: Temporal Speed-up is A Simple Trick for Long-form Music Composing","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2605.27840","title":"LoSATok: Low-Dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.16969","title":"Probing Low Frame Rate Degradation in Neural Audio Codecs","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.25285","title":"A Training-Free Proactive Defense Against Partial Speech Manipulation via Self-Embedding Steganography","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.25289","title":"Combining Self-Embedding Audio Watermarking with Ultra-Low-Bitrate Neural Codecs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.12563","title":"TokenMapper: A Step Toward Interoperable Speech Token Translation","created":"2026-09-11","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":"2610.04651","title":"GS-Codec: A Gaussian-Splatting Bottleneck for Neural Audio Coding","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}