{"total":152,"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":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179,"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":"2402.15116","title":"Large Multimodal Agents: A Survey","created":"2024-02-23","cited_by_count":105,"area":"lr"},{"id":"2506.21619","title":"IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech","created":"2025-06-23","cited_by_count":90,"area":null},{"id":"2407.08551","title":"Autoregressive Speech Synthesis without Vector Quantization","created":"2024-07-11","cited_by_count":65,"area":null},{"id":"2309.02285","title":"PromptTTS 2: Describing and Generating Voices with Text Prompt","created":"2023-09-05","cited_by_count":48,"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":"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":"2406.11427","title":"DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors","created":"2024-06-17","cited_by_count":32,"area":"diffusion"},{"id":"2502.05236","title":"Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance","created":"2025-02-07","cited_by_count":27,"area":"alignment"},{"id":"2404.14700","title":"FlashSpeech: Efficient Zero-Shot Speech Synthesis","created":"2024-04-23","cited_by_count":24,"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":"2412.12009","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","created":"2024-12-16","cited_by_count":21,"area":"inference"},{"id":"2409.08731","title":"DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset","created":"2024-09-13","cited_by_count":20,"area":"diffusion"},{"id":"2409.04927","title":"Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue","created":"2024-09-07","cited_by_count":16,"area":"lr"},{"id":"2409.05356","title":"IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS","created":"2024-09-09","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":"2603.18090","title":"MOSS-TTS Technical Report","created":"2026-03-18","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":"2411.00121","title":"I Can Hear You: Selective Robust Training for Deepfake Audio Detection","created":"2024-10-31","cited_by_count":13,"area":null},{"id":"2408.07547","title":"PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation","created":"2024-08-14","cited_by_count":12,"area":"diffusion"},{"id":"2309.09493","title":"HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform","created":"2023-09-18","cited_by_count":11,"area":null},{"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":"2411.19537","title":"Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook","created":"2024-11-29","cited_by_count":10,"area":null},{"id":"2503.12042","title":"Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing","created":"2025-03-15","cited_by_count":10,"area":null},{"id":"2603.25406","title":"MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation","created":"2026-03-26","cited_by_count":10,"area":"vla"},{"id":"2402.12220","title":"Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2404.15854","title":"CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning","created":"2024-04-24","cited_by_count":9,"area":null},{"id":"2507.05177","title":"OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model","created":"2025-07-07","cited_by_count":9,"area":null},{"id":"2602.03420","title":"CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering","created":"2026-02-03","cited_by_count":9,"area":"mechinterp"},{"id":"2506.19441","title":"TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems","created":"2025-06-24","cited_by_count":8,"area":null},{"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":"2408.11849","title":"Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation","created":"2024-08-13","cited_by_count":7,"area":null},{"id":"2409.09351","title":"E1 TTS: Simple and Fast Non-Autoregressive TTS","created":"2024-09-14","cited_by_count":7,"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":"2411.12719","title":"Rethinking MUSHRA: Addressing Modern Challenges in Text-to-Speech Evaluation","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2404.18094","title":"USAT: A Universal Speaker-Adaptive Text-to-Speech Approach","created":"2024-04-28","cited_by_count":6,"area":null},{"id":"2406.05968","title":"Prompting Large Language Models with Audio for General-Purpose Speech Summarization","created":"2024-06-10","cited_by_count":6,"area":"lr"},{"id":"2410.15042","title":"Adversarial Training: A Survey","created":"2024-10-19","cited_by_count":6,"area":null},{"id":"2501.08468","title":"Selective Attention Merging for low resource tasks: A case study of Child ASR","created":"2025-01-14","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":"2505.01263","title":"FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing","created":"2025-05-02","cited_by_count":6,"area":"diffusion"},{"id":"2509.21108","title":"VoiceBBQ: Investigating Effect of Content and Acoustics in Social Bias of Spoken Language Model","created":"2025-09-25","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":"2505.14910","title":"TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2507.08983","title":"Exploiting Leaderboards for Large-Scale Distribution of Malicious Models","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2509.14270","title":"SpeechWeave: Diverse Multilingual Synthetic Text & Audio Data Generation Pipeline for Training Text to Speech Models","created":"2025-09-15","cited_by_count":5,"area":null},{"id":"2509.15655","title":"Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2510.25054","title":"Evaluating Emotion Recognition in Spoken Language Models on Emotionally Incongruent Speech","created":"2025-10-29","cited_by_count":5,"area":null},{"id":"2406.04906","title":"RU-AI: A Large Multimodal Dataset for Machine-Generated Content Detection","created":"2024-06-07","cited_by_count":4,"area":null},{"id":"2505.00579","title":"Voice Cloning: Comprehensive Survey","created":"2025-05-01","cited_by_count":4,"area":null},{"id":"2505.18609","title":"RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2505.23962","title":"Can Emotion Fool Anti-spoofing?","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2507.20091","title":"ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models","created":"2025-07-27","cited_by_count":4,"area":null},{"id":"2508.04179","title":"The State Of TTS: A Case Study with Human Fooling Rates","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2510.04908","title":"How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning","created":"2025-10-06","cited_by_count":4,"area":null},{"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":"2307.09435","title":"SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANs","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2502.16794","title":"AAD-LLM: Neural Attention-Driven Auditory Scene Understanding","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2507.21138","title":"TTS-1 Technical Report","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2509.19231","title":"Finding My Voice: Generative Reconstruction of Disordered Speech for Automated Clinical Evaluation","created":"2025-09-23","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":"2601.11141","title":"FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2603.16874","title":"Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Models","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2604.08125","title":"PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2404.10419","title":"MAD Speech: Measures of Acoustic Diversity of Speech","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2407.13435","title":"Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2410.17901","title":"ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigrams","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2412.00055","title":"High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2412.11795","title":"ProsodyFM: Unsupervised Phrasing and Intonation Control for Intelligible Speech Synthesis","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2502.01084","title":"Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2508.12854","title":"E3RG: Building Explicit Emotion-driven Empathetic Response Generation System with Multimodal Large Language Model","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2603.02781","title":"Scores Know Bobs Voice: Speaker Impersonation Attack","created":"2026-03-03","cited_by_count":2,"area":null},{"id":"2404.04645","title":"HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks","created":"2024-04-06","cited_by_count":1,"area":null},{"id":"2407.13153","title":"Preset-Voice Matching for Privacy Regulated Speech-to-Speech Translation Systems","created":"2024-07-18","cited_by_count":1,"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":"2409.11261","title":"Kahaani: A Multimodal Co-Creative Storytelling System","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2410.23320","title":"Lina-Speech: Gated Linear Attention and Initial-State Tuning for Multi-Sample Prompting Text-To-Speech Synthesis","created":"2024-10-30","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":"2503.05464","title":"Automatic Teaching Platform on Vision Language Retrieval Augmented Generation","created":"2025-03-07","cited_by_count":1,"area":"rag"},{"id":"2505.19119","title":"CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloning","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2505.20606","title":"Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2505.23308","title":"Spoken question answering for visual queries","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.12197","title":"Quantize More, Lose Less: Autoregressive Generation from Residually Quantized Speech Representations","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2508.09389","title":"ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2509.21125","title":"Acoustic-based Gender Differentiation in Speech-aware Language Models","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2510.20223","title":"Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations","created":"2025-10-23","cited_by_count":1,"area":"mllm"},{"id":"2606.21343","title":"An Evaluation Framework for Text-to-Speech Voice Reconstruction","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2609.03502","title":"Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2406.10223","title":"Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2406.10514","title":"GTR-Voice: Articulatory Phonetics Informed Controllable Expressive Speech Synthesis","created":"2024-06-15","cited_by_count":0,"area":null},{"id":"2407.17167","title":"Zero-Shot vs. Few-Shot Multi-Speaker TTS Using Pre-trained Czech SpeechT5 Model","created":"2024-07-24","cited_by_count":0,"area":null},{"id":"2409.20374","title":"Word-wise intonation model for cross-language TTS systems","created":"2024-09-30","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":"2504.08524","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":"2504.16234","title":"Using Phonemes in cascaded S2S translation pipeline","created":"2025-04-22","cited_by_count":0,"area":null},{"id":"2506.03020","title":"InfiniteAudio: Infinite-Length Audio Generation with Consistency","created":"2025-06-03","cited_by_count":0,"area":"diffusion"}],"next_cursor":"100"}