{"total":101,"rows":[{"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":"2411.02038","title":"Addressing Representation Collapse in Vector Quantized Models with One Linear Layer","created":"2024-11-04","cited_by_count":80,"area":null},{"id":"2407.08551","title":"Autoregressive Speech Synthesis without Vector Quantization","created":"2024-07-11","cited_by_count":65,"area":null},{"id":"2512.23808","title":"MiMo-Audio: Audio Language Models are Few-Shot Learners","created":"2025-12-29","cited_by_count":65,"area":null},{"id":"2308.06873","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","created":"2023-08-14","cited_by_count":64,"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":"2406.07855","title":"VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment","created":"2024-06-12","cited_by_count":38,"area":null},{"id":"2511.03334","title":"UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions","created":"2025-11-05","cited_by_count":38,"area":null},{"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":"2506.23325","title":"XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs","created":"2025-06-29","cited_by_count":23,"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":"2511.05516","title":"Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation","created":"2025-10-26","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":"2602.18899","title":"[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic","created":"2026-02-21","cited_by_count":12,"area":null},{"id":"2503.06940","title":"CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing","created":"2025-03-10","cited_by_count":11,"area":null},{"id":"2509.14515","title":"From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Models","created":"2025-09-18","cited_by_count":10,"area":null},{"id":"2512.13674","title":"Towards Interactive Intelligence for Digital Humans","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2409.06109","title":"Estimating the Completeness of Discrete Speech Units","created":"2024-09-09","cited_by_count":9,"area":null},{"id":"2503.16956","title":"From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech","created":"2025-03-21","cited_by_count":9,"area":null},{"id":"2504.02433","title":"OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking","created":"2025-04-03","cited_by_count":9,"area":null},{"id":"2509.16195","title":"FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation","created":"2025-09-19","cited_by_count":9,"area":null},{"id":"2505.19206","title":"SpeakStream: Streaming Text-to-Speech with Interleaved Data","created":"2025-05-25","cited_by_count":8,"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":"2412.10208","title":"Efficient Generative Modeling with Residual Vector Quantization-Based Tokens","created":"2024-12-13","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":"2406.04467","title":"Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis","created":"2024-06-06","cited_by_count":6,"area":null},{"id":"2504.09839","title":"SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis","created":"2025-04-14","cited_by_count":6,"area":null},{"id":"2404.19622","title":"Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis","created":"2024-04-30","cited_by_count":5,"area":null},{"id":"2405.07682","title":"FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation","created":"2024-05-13","cited_by_count":5,"area":null},{"id":"2508.16332","title":"Vevo2: A Unified and Controllable Framework for Speech and Singing Voice Generation","created":"2025-08-22","cited_by_count":5,"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":"2604.01929","title":"Woosh: A Sound Effects Foundation Model","created":"2026-04-02","cited_by_count":4,"area":null},{"id":"2505.14351","title":"FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for \\\"U-Tsang, Amdo and Kham Speech Dataset Generation","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2505.19273","title":"Eta-WavLM: Efficient Speaker Identity Removal in Self-Supervised Speech Representations Using a Simple Linear Equation","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2505.19679","title":"KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2605.06407","title":"WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2406.07801","title":"PolySpeech: Exploring Unified Multitask Speech Models for Competitiveness with Single-task Models","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2407.01291","title":"Lightweight Zero-shot Text-to-Speech with Mixture of Adapters","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2502.20040","title":"CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2503.23108","title":"SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System","created":"2025-03-29","cited_by_count":2,"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":"2509.09550","title":"Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-rates","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2601.22306","title":"Sylber 2.0: A Universal Syllable Embedding","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.06602","title":"Scaling Speech Tokenizers with Diffusion Autoencoders","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2608.24168","title":"FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2502.02703","title":"Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2505.13181","title":"Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.16972","title":"From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2506.16738","title":"LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2507.03887","title":"Traceable TTS: Toward Watermark-Free TTS with Strong Traceability","created":"2025-07-05","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":"2509.04072","title":"Computational Narrative Understanding for Expressive Text-to-Speech","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2509.26471","title":"On Deepfake Voice Detection -- It's All in the Presentation","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.25228","title":"'Studies for': A Human-AI Co-Creative Sound Artwork Using a Real-time Multi-channel Sound Generation Model","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2510.25566","title":"PitchFlower: A flow-based neural audio codec with pitch controllability","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2606.09553","title":"OpenBibleTTS: Large-Scale Speech Resources and TTS Models for Low-Resource Languages","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.23176","title":"Synthesizing the Lombard Effect: Multi-Level Control of Speech Clarity and Vocal Effort in TTS","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2609.03107","title":"CRAW: Codec Robust Audio Watermarking","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2505.24498","title":"Efficient Neural and Numerical Methods for High-Quality Online Speech Spectrogram Inversion via Gradient Theorem","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.21202","title":"Combolutional Neural Networks","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2509.04345","title":"AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2509.13049","title":"Spiking Vocos: An Energy-Efficient Neural Vocoder","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.18060","title":"TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Framework for \\\"U-Tsang, Amdo and Kham Speech Dataset Generation","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2511.07099","title":"E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis","created":"2025-11-10","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":"2512.05126","title":"SyncVoice: Simple and Effective Automatic Video Dubbing with Vision-Augmented TTS","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.16519","title":"Pseudo-Cepstrum: Pitch Modification for Mel-Based Neural Vocoders","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2601.14472","title":"Prosody-Guided Harmonic Attention for Phase-Coherent Neural Vocoding in the Complex Spectrum","created":"2026-01-20","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":"2602.15909","title":"Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2602.20113","title":"StyleStream: Real-Time Zero-Shot Voice Style Conversion","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.01622","title":"More Data, Fewer Diacritics: Scaling Arabic TTS","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.07285","title":"Fast and Flexible Audio Bandwidth Extension via Vocos","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2603.09234","title":"StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.11589","title":"Toward Complex-Valued Neural Networks for Waveform Generation","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2603.15326","title":"Tagarela - A Portuguese speech dataset from podcasts","created":"2026-03-16","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":"2604.14606","title":"UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations","created":"2026-04-16","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":"2606.04418","title":"CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.11828","title":"Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions","created":"2026-06-10","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":"2606.14750","title":"Pixel-TTS: Image based Text Rendering for Robust Text-to-Speech","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.26534","title":"VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.27627","title":"HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models","created":"2026-06-26","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":"2607.27775","title":"RIPPLE: Generating Multi-Channel Phase, Not Recovering It","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.18661","title":"X2Streaming-TTS: Causal Token-Level Text-to-Speech from Streaming Text with Speech-State Inheritance","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.26146","title":"Vagdhenu: A Vrutta (Meter) Aware Shloka-to-Chant (TTS) System for Sanskrit","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2609.11642","title":"ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding","created":"2026-09-10","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":"2609.13045","title":"Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.27489","title":"Passing: An Endless Journey through Reconstructed Spacetime with AI-Generated Sound","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.29405","title":"Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30975","title":"A Comprehensive Study of Content Representations for Speech Synthesis","created":"2026-09-25","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},{"id":"2610.06817","title":"Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":"100"}