{"total":35,"rows":[{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"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":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72,"area":null},{"id":"2411.19842","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","created":"2024-11-29","cited_by_count":49,"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":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"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":"2406.01205","title":"ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control","created":"2024-06-03","cited_by_count":17,"area":null},{"id":"2508.16790","title":"TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling","created":"2025-08-22","cited_by_count":13,"area":null},{"id":"2410.15764","title":"LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec","created":"2024-10-21","cited_by_count":7,"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":"2601.23174","title":"Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2409.17635","title":"FlowMAC: Conditional Flow Matching for Audio Coding at Low Bit Rates","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2506.00800","title":"CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2510.00499","title":"MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2602.06602","title":"Scaling Speech Tokenizers with Diffusion Autoencoders","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2504.08470","title":"On the Design of Diffusion-based Neural Speech Codecs","created":"2025-04-11","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":"2507.12825","title":"Autoregressive Speech Enhancement via Acoustic Tokens","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2510.16718","title":"U-Codec: Ultra Low Frame-rate Neural Speech Codec for Fast High-fidelity Speech Generation","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2605.11192","title":"Exploring Token-Space Manipulation in Latent Audio Tokenizers","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2607.15755","title":"AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis","created":"2026-07-17","cited_by_count":1,"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":"2511.20224","title":"DuoTok: Source-Aware Dual-Track Music Tokenization for Vocal-Accompaniment Generation","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.01537","title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2512.21653","title":"Decoder-Side Semantic Conditioning for Low-Bitrate Neural Speech Compression","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2602.15082","title":"S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2607.29363","title":"Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens","created":"2026-07-31","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":"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},{"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}