{"total":97,"rows":[{"id":"2410.06885","title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","created":"2024-10-09","cited_by_count":361,"area":"diffusion"},{"id":"2403.03100","title":"NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models","created":"2024-03-05","cited_by_count":226,"area":"diffusion"},{"id":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161,"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":"2406.05370","title":"VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers","created":"2024-06-08","cited_by_count":122,"area":null},{"id":"2407.04051","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","created":"2024-07-04","cited_by_count":122,"area":null},{"id":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102,"area":"vla"},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87,"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":"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":"2402.12786","title":"Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations","created":"2024-02-20","cited_by_count":45,"area":null},{"id":"2405.00233","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","created":"2024-04-30","cited_by_count":45,"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":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40,"area":null},{"id":"2504.04953","title":"M-Prometheus: A Suite of Open Multilingual LLM Judges","created":"2025-04-07","cited_by_count":38,"area":null},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2311.12454","title":"HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis","created":"2023-11-21","cited_by_count":35,"area":null},{"id":"2406.05551","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis","created":"2024-06-08","cited_by_count":34,"area":"diffusion"},{"id":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32,"area":"mllm"},{"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":"2502.13128","title":"SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation","created":"2025-02-18","cited_by_count":29,"area":null},{"id":"2305.19269","title":"Make-A-Voice: Unified Voice Synthesis With Discrete Representation","created":"2023-05-30","cited_by_count":27,"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":"2406.10735","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?","created":"2024-06-15","cited_by_count":24,"area":null},{"id":"2410.04029","title":"SyllableLM: Learning Coarse Semantic Units for Speech Language Models","created":"2024-10-05","cited_by_count":24,"area":null},{"id":"2406.02328","title":"SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models","created":"2024-06-04","cited_by_count":23,"area":"diffusion"},{"id":"2412.06602","title":"Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2312.00834","title":"AV-RIR: Audio-Visual Room Impulse Response Estimation","created":"2023-11-30","cited_by_count":20,"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":"2408.13893","title":"SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models","created":"2024-08-25","cited_by_count":17,"area":"diffusion"},{"id":"2602.21736","title":"Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild","created":"2026-02-25","cited_by_count":15,"area":"vla"},{"id":"2402.05706","title":"Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2408.16221","title":"SSDM: Scalable Speech Dysfluency Modeling","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2408.09027","title":"Efficient Autoregressive Audio Modeling via Next-Scale Prediction","created":"2024-08-16","cited_by_count":11,"area":"diffusion"},{"id":"2409.12117","title":"Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference","created":"2024-09-18","cited_by_count":11,"area":null},{"id":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2502.20263","title":"Vector-Quantized Vision Foundation Models for Object-Centric Learning","created":"2025-02-27","cited_by_count":11,"area":null},{"id":"2503.00084","title":"InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation","created":"2025-02-28","cited_by_count":11,"area":"diffusion"},{"id":"2507.22920","title":"Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey","created":"2025-07-21","cited_by_count":8,"area":"mllm"},{"id":"2402.03407","title":"Enhancing the Stability of LLM-based Speech Generation Systems through Self-Supervised Representations","created":"2024-02-05","cited_by_count":7,"area":null},{"id":"2406.08112","title":"Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2503.14919","title":"GenM$^3$: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2505.14470","title":"PAST: Phonetic-Acoustic Speech Tokenizer","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2601.01373","title":"UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2603.00632","title":"Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale","created":"2026-02-28","cited_by_count":6,"area":null},{"id":"2401.01099","title":"Efficient Parallel Audio Generation using Group Masked Language Modeling","created":"2024-01-02","cited_by_count":5,"area":null},{"id":"2401.01272","title":"MOC-RVQ: Multilevel Codebook-Assisted Digital Generative Semantic Communication","created":"2024-01-02","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":"2410.15017","title":"DM-Codec: Distilling Multimodal Representations for Speech Tokenization","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2411.02299","title":"Grouped Discrete Representation for Object-Centric Learning","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2409.05784","title":"Vector Quantized Diffusion Model Based Speech Bandwidth Extension","created":"2024-09-09","cited_by_count":4,"area":"diffusion"},{"id":"2410.12399","title":"SF-Speech: Straightened Flow for Zero-Shot Voice Clone","created":"2024-10-16","cited_by_count":4,"area":"diffusion"},{"id":"2411.17867","title":"RankMap: Priority-Aware Multi-DNN Manager for Heterogeneous Embedded Devices","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2411.19402","title":"On the Role of Discrete Representation in Sparse Mixture of Experts","created":"2024-11-28","cited_by_count":4,"area":"moe"},{"id":"2312.03406","title":"Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach","created":"2023-12-06","cited_by_count":3,"area":null},{"id":"2404.02702","title":"PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2410.17081","title":"Continuous Speech Tokenizer in Text To Speech","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2411.00664","title":"Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2503.12814","title":"Versatile Physics-based Character Control with Hybrid Latent Representation","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2510.12721","title":"CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2509.01390","title":"Analysing the Language of Neural Audio Codecs","created":"2025-09-01","cited_by_count":2,"area":null},{"id":"2409.11003","title":"Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation","created":"2024-09-17","cited_by_count":1,"area":"distill"},{"id":"2410.01350","title":"Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2505.05589","title":"ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2505.12404","title":"Hyperbolic Residual Quantization: Discrete Representations for Data with Latent Hierarchies","created":"2025-05-18","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":"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":"2601.22556","title":"VocBulwark: Towards Practical Generative Speech Watermarking via Additional-Parameter Injection","created":"2026-01-30","cited_by_count":1,"area":"safety"},{"id":"2602.15491","title":"The Equalizer: Introducing Shape-Gain Decomposition in Neural Audio Codecs","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2605.01790","title":"Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2608.31037","title":"Language-Statistical Analysis of Neural Audio Codec Tokens Across Architectures, Corpora, and Noise Conditions","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2410.04690","title":"SegINR: Segment-wise Implicit Neural Representation for Sequence Alignment in Neural Text-to-Speech","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2411.05961","title":"Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Models","created":"2024-11-08","cited_by_count":0,"area":"mllm"},{"id":"2504.08524","title":"USM-VC: Mitigating Timbre Leakage with Universal Semantic Mapping Residual Block for Voice Conversion","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2504.14113","title":"Lightweight Road Environment Segmentation using Vector Quantization","created":"2025-04-19","cited_by_count":0,"area":null},{"id":"2505.19342","title":"ASTRA: Communication-Efficient Acceleration for Multi-Device Transformer Inference","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2508.02521","title":"Towards Reliable Audio Deepfake Attribution and Model Recognition: A Multi-Level Autoencoder-Based Framework","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.11598","title":"Representing Speech Through Autoregressive Prediction of Cochlear Tokens","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2509.02349","title":"AudioCodecBench: A Comprehensive Benchmark for Audio Codec Evaluation","created":"2025-09-02","cited_by_count":0,"area":"mllm"},{"id":"2509.11425","title":"FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs","created":"2025-09-14","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":"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":"2601.07958","title":"LJ-Spoof: A Generatively Varied Corpus for Audio Anti-Spoofing and Synthesis Source Tracing","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2602.11477","title":"SLD-L2S: Hierarchical Subspace Latent Diffusion for High-Fidelity Lip to Speech Synthesis","created":"2026-02-12","cited_by_count":0,"area":"diffusion"},{"id":"2602.23387","title":"Hello-Chat: Towards Realistic Social Audio Interactions","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.12246","title":"TokenSE: a Mamba-based discrete token speech enhancement framework for cochlear implants","created":"2026-04-14","cited_by_count":0,"area":"ssm"},{"id":"2605.31521","title":"UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.12940","title":"Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","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":"2609.26342","title":"Geometry-Aware Hyperbolic Residual-Quantized Variational Autoencoders","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.01492","title":"Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization","created":"2026-10-01","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}