{"total":31,"rows":[{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771,"area":null},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687,"area":null},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78,"area":null},{"id":"2203.13086","title":"HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement","created":"2022-03-24","cited_by_count":49,"area":null},{"id":"2309.07405","title":"FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec","created":"2023-09-14","cited_by_count":44,"area":null},{"id":"2405.04880","title":"The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio","created":"2024-05-08","cited_by_count":31,"area":null},{"id":"2505.18185","title":"BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals","created":"2025-05-18","cited_by_count":27,"area":null},{"id":"2406.04328","title":"The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning","created":"2024-06-06","cited_by_count":21,"area":null},{"id":"2506.02098","title":"LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale","created":"2025-06-02","cited_by_count":20,"area":null},{"id":"2202.07273","title":"SpeechPainter: Text-conditioned Speech Inpainting","created":"2022-02-15","cited_by_count":17,"area":null},{"id":"2204.03042","title":"FFC-SE: Fast Fourier Convolution for Speech Enhancement","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2410.20916","title":"NeuGPT: Unified multi-modal Neural GPT","created":"2024-10-28","cited_by_count":7,"area":null},{"id":"2305.05591","title":"AudioSlots: A slot-centric generative model for audio separation","created":"2023-05-09","cited_by_count":5,"area":null},{"id":"2406.00146","title":"A Survey of Deep Learning Audio Generation Methods","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2407.11828","title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2410.15017","title":"DM-Codec: Distilling Multimodal Representations for Speech Tokenization","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2506.02979","title":"Towards a Japanese Full-duplex Spoken Dialogue System","created":"2025-06-03","cited_by_count":5,"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":"2508.05207","title":"SpectroStream: A Versatile Neural Codec for General Audio","created":"2025-08-07","cited_by_count":4,"area":null},{"id":"2512.01443","title":"MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classification","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2507.18897","title":"HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2402.01571","title":"Spiking Music: Audio Compression with Event Based Auto-encoders","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2603.10371","title":"Speech Codec Probing from Semantic and Phonetic Perspectives","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2606.09605","title":"Next-Token Prediction Learns Generalisable Representations of Sleep Physiology","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2506.06732","title":"Neural Spectral Band Generation for Audio Coding","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2506.22321","title":"SUBARU: A Practical Approach to Power Saving in Hearables Using SUB-Nyquist Audio Resolution Upsampling","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2511.12074","title":"MF-Speech: Achieving Fine-Grained and Compositional Control in Speech Generation via Factor Disentanglement","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2606.04103","title":"The Differentiable Auditory Loop (DAL): An ML Framework for Hyper-Personalized Hearing Aids","created":"2026-06-02","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}