{"total":122,"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":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288,"area":"diffusion"},{"id":"2505.17589","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","created":"2025-05-23","cited_by_count":150,"area":"diffusion"},{"id":"2411.00774","title":"Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM","created":"2024-11-01","cited_by_count":141,"area":"mllm"},{"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":"2503.01710","title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","created":"2025-03-03","cited_by_count":113,"area":null},{"id":"2502.04128","title":"Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis","created":"2025-02-06","cited_by_count":70,"area":"lr"},{"id":"2407.08551","title":"Autoregressive Speech Synthesis without Vector Quantization","created":"2024-07-11","cited_by_count":65,"area":null},{"id":"2502.03930","title":"DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation","created":"2025-02-06","cited_by_count":57,"area":"diffusion"},{"id":"2412.08635","title":"Multimodal Latent Language Modeling with Next-Token Diffusion","created":"2024-12-11","cited_by_count":48,"area":"mllm"},{"id":"2504.05108","title":"Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning","created":"2025-04-07","cited_by_count":46,"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":"2502.18924","title":"MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis","created":"2025-02-26","cited_by_count":41,"area":"diffusion"},{"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":"2504.02407","title":"F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization","created":"2025-04-03","cited_by_count":24,"area":"diffusion"},{"id":"2503.14345","title":"MoonCast: High-Quality Zero-Shot Podcast Generation","created":"2025-03-18","cited_by_count":18,"area":null},{"id":"2410.08035","title":"IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities","created":"2024-10-09","cited_by_count":17,"area":null},{"id":"2410.21951","title":"Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding","created":"2024-10-29","cited_by_count":17,"area":"inference"},{"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":"2407.12707","title":"TTSDS -- Text-to-Speech Distribution Score","created":"2024-07-17","cited_by_count":14,"area":null},{"id":"2410.21620","title":"Asynchronous Tool Usage for Real-Time Agents","created":"2024-10-28","cited_by_count":13,"area":"agents"},{"id":"2410.16726","title":"Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap","created":"2024-10-22","cited_by_count":12,"area":null},{"id":"2504.02386","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","created":"2025-04-03","cited_by_count":11,"area":null},{"id":"2506.02863","title":"CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2410.13839","title":"Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding","created":"2024-10-17","cited_by_count":10,"area":"inference"},{"id":"2504.10352","title":"Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis","created":"2025-04-14","cited_by_count":10,"area":null},{"id":"2409.09098","title":"AccentBox: Towards High-Fidelity Zero-Shot Accent Generation","created":"2024-09-13","cited_by_count":9,"area":null},{"id":"2502.15218","title":"ESPnet-SpeechLM: An Open Speech Language Model Toolkit","created":"2025-02-21","cited_by_count":9,"area":"agents"},{"id":"2502.19548","title":"When Large Language Models Meet Speech: A Survey on Integration Approaches","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2409.14993","title":"Multi-modal Generative AI: Multi-modal LLMs, Diffusions, and the Unification","created":"2024-09-23","cited_by_count":8,"area":"mllm"},{"id":"2502.04519","title":"GenVC: Self-Supervised Zero-Shot Voice Conversion","created":"2025-02-06","cited_by_count":8,"area":null},{"id":"2502.11128","title":"FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching","created":"2025-02-16","cited_by_count":8,"area":"diffusion"},{"id":"2507.14988","title":"DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis","created":"2025-07-20","cited_by_count":8,"area":"diffusion"},{"id":"2409.10058","title":"StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion","created":"2024-09-16","cited_by_count":7,"area":"diffusion"},{"id":"2504.20629","title":"AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation","created":"2025-04-29","cited_by_count":7,"area":"diffusion"},{"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":"2506.08967","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2511.03601","title":"Step-Audio-EditX Technical Report","created":"2025-11-05","cited_by_count":7,"area":null},{"id":"2410.15316","title":"Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant","created":"2024-10-20","cited_by_count":6,"area":null},{"id":"2410.11097","title":"DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis","created":"2024-10-14","cited_by_count":5,"area":"diffusion"},{"id":"2410.16048","title":"Speech Synthesis From Continuous Features Using Per-Token Latent Diffusion","created":"2024-10-21","cited_by_count":5,"area":"diffusion"},{"id":"2412.16846","title":"KALL-E:Autoregressive Speech Synthesis with Next-Distribution Prediction","created":"2024-12-22","cited_by_count":5,"area":null},{"id":"2506.00350","title":"DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model","created":"2025-05-31","cited_by_count":5,"area":"diffusion"},{"id":"2409.17452","title":"Description-based Controllable Text-to-Speech with Cross-Lingual Voice Control","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2410.12399","title":"SF-Speech: Straightened Flow for Zero-Shot Voice Clone","created":"2024-10-16","cited_by_count":4,"area":"diffusion"},{"id":"2505.00579","title":"Voice Cloning: Comprehensive Survey","created":"2025-05-01","cited_by_count":4,"area":null},{"id":"2505.12800","title":"OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching","created":"2025-05-19","cited_by_count":4,"area":"diffusion"},{"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":"2510.13344","title":"UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE","created":"2025-10-15","cited_by_count":4,"area":"moe"},{"id":"2510.22795","title":"SAO-Instruct: Free-form Audio Editing using Natural Language Instructions","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2604.11103","title":"ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing","created":"2026-04-13","cited_by_count":4,"area":null},{"id":"2505.19669","title":"Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2506.12570","title":"StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling","created":"2025-06-14","cited_by_count":3,"area":null},{"id":"2507.22746","title":"Next Tokens Denoising for Speech Synthesis","created":"2025-07-30","cited_by_count":3,"area":"diffusion"},{"id":"2508.08957","title":"QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2509.19883","title":"CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2510.12210","title":"DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2511.12347","title":"VoiceCraft-X: Unifying Multilingual, Voice-Cloning Speech Synthesis and Speech Editing","created":"2025-11-15","cited_by_count":3,"area":null},{"id":"2604.10065","title":"ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models","created":"2026-04-11","cited_by_count":3,"area":null},{"id":"2408.10853","title":"Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio?","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2411.14642","title":"VQalAttent: a Transparent Speech Generation Pipeline based on Transformer-learned VQ-VAE Latent Space","created":"2024-11-22","cited_by_count":2,"area":null},{"id":"2502.11094","title":"SyncSpeech: Efficient and Low-Latency Text-to-Speech based on Temporal Masked Transformer","created":"2025-02-16","cited_by_count":2,"area":null},{"id":"2508.21407","title":"DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2603.07534","title":"Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2603.14267","title":"DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization","created":"2026-03-15","cited_by_count":2,"area":"diffusion"},{"id":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2408.06922","title":"Temporal Variability and Multi-Viewed Self-Supervised Representations to Tackle the ASVspoof5 Deepfake Challenge","created":"2024-08-13","cited_by_count":1,"area":null},{"id":"2410.06572","title":"Can DeepFake Speech be Reliably Detected?","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2410.11086","title":"JOOCI: a Framework for Learning Comprehensive Speech Representations","created":"2024-10-14","cited_by_count":1,"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":"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":"2508.08715","title":"MultiGen: Child-Friendly Multilingual Speech Generator with LLMs","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2508.09767","title":"UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speech","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2509.06277","title":"No Encore: Unlearning as Opt-Out in Music Generation","created":"2025-09-08","cited_by_count":1,"area":"safety"},{"id":"2509.09748","title":"DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration","created":"2025-09-11","cited_by_count":1,"area":"diffusion"},{"id":"2510.04593","title":"UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models","created":"2025-10-06","cited_by_count":1,"area":"diffusion"},{"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":"2510.20210","title":"Vox-Evaluator: Enhancing Stability and Fidelity for Zero-shot TTS with A Multi-Level Evaluator","created":"2025-10-23","cited_by_count":1,"area":"diffusion"},{"id":"2511.17555","title":"Speech Recognition Model Improves Text-to-Speech Synthesis using Fine-Grained Reward","created":"2025-11-12","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":"2603.05310","title":"Latent-Mark: An Audio Watermark Robust to Neural Codec Compression","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.07550","title":"Learning-free L2-Accented Speech Generation using Phonological Rules","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2603.08174","title":"MERLIN: Building Low-SNR Robust Multimodal LLMs for Electromagnetic Signals","created":"2026-03-09","cited_by_count":1,"area":"mllm"},{"id":"2605.27376","title":"Unlocking Fine-Grained and Within-Utterance Speaking Style Control in Prompt-Based Text-to-Speech Models","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2606.03455","title":"WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling","created":"2026-06-02","cited_by_count":1,"area":"diffusion"},{"id":"2606.18485","title":"MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.20266","title":"Transcript-Free Flow-Matching Text-to-Speech via Speech Feature Conditioning","created":"2026-06-18","cited_by_count":1,"area":"diffusion"},{"id":"2606.25403","title":"CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.28351","title":"Teffic-Audio: Tell Fact from Fiction","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.28970","title":"Diagnose, Then Refine: A Closed-Loop TTS System with AudioLLM-Guided Correction","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2410.21670","title":"Sequential choice in ordered bundles","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2501.08566","title":"Towards Lightweight and Stable Zero-shot TTS with Self-distilled Representation Disentanglement","created":"2025-01-15","cited_by_count":0,"area":null},{"id":"2504.12339","title":"GOAT-TTS: Expressive and Realistic Speech Generation via A Dual-Branch LLM","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2505.22054","title":"Voice Adaptation for Swiss German","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2506.05368","title":"Speaking images. A novel framework for the automated self-description of artworks","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2508.12001","title":"FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech Synthesis","created":"2025-08-16","cited_by_count":0,"area":"moe"},{"id":"2509.05863","title":"LatinX: Aligning a Multilingual TTS Model with Direct Preference Optimization","created":"2025-09-06","cited_by_count":0,"area":"alignment"},{"id":"2509.19592","title":"Frame-Stacked Local Transformers For Efficient Multi-Codebook Speech Generation","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2510.02848","title":"Flamed-TTS: Flow Matching Attention-Free Models for Efficient Generating and Dynamic Pacing Zero-shot Text-to-Speech","created":"2025-10-03","cited_by_count":0,"area":"diffusion"}],"next_cursor":"100"}