Key papers

• Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models (2025)
  Arushi Goel and Sreyan Ghosh and Jaehyeon Kim and Sonal Kumar and Zhifeng Kong and Sang-gil Lee and Chao-Han Huck Yang and Ramani Duraiswami and Dinesh Manocha and Rafael Valle and Bryan Catanzaro
  13.42
• StepAudio 2.5 Technical Report (2026)
  Bin Lin et al.
  12.36
• MinMo: A Multimodal Large Language Model for Seamless Voice Interaction (2025)
  Qian Chen et al.
  11.99
• CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech (2025)
  Helin Wang et al.
  11.00
• Discrete Diffusion Models: A Unified Framework from Tokenization to Generation (2026)
  Ye Yuan et al.
  10.48
• SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue (2026)
  Ruiqi Li et al.
  10.23
• DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion (2025)
  Ziqian Ning et al.
  10.21
• MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models (2026)
  Yitian Gong et al.
  10.13
• Generative Adversarial Phonology: Modeling Unsupervised Phonetic And Phonological Learning With Neural Networks (2020)
  Gašper Beguš
  10.07
• MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder (2025)
  Bowen Zhang et al.
  9.94
• MiDashengLM: Efficient Audio Understanding with General Audio Captions (2025)
  Heinrich Dinkel et al.
  9.30
• FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot (2025)
  Kun Xie et al.
  9.28
• VibeVoice Technical Report (2025)
  Zhiliang Peng et al.
  8.71
• MoonCast: High-Quality Zero-Shot Podcast Generation (2025)
  Zeqian Ju et al.
  8.52
• KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation (2025)
  Yoonjin Chung et al.
  8.47
• DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec for Speech Generation (2025)
  Jiaqi Li et al.
  8.34
• PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models (2026)
  Rajarshi Roy et al.
  8.18
• FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation (2025)
  Yuxuan Jiang et al.
  7.86
• SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement (2025)
  Chenyu Yang et al.
  7.80
• Covo-Audio Technical Report (2026)
  Wenfu Wang et al.
  7.68
• DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformers (2025)
  Heitor R. Guimar\~aes et al.
  7.55
• AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation (2025)
  Le Wang et al.
  7.47
• MOSS-TTS Technical Report (2026)
  Yitian Gong et al.
  7.45
• Fast Text-to-Audio Generation with Adversarial Post-Training (2025)
  Zachary Novack et al.
  7.30
• T5Gemma-TTS Technical Report (2026)
  Chihiro Arata and Kiyoshi Kurihara
  7.18
• A Syllable-structured, Contextually-based Conditionally Generation Of Chinese Lyrics (2019)
  Xu Lu, Jie Wang, Bojin Zhuang, et al.
  7.16
• TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis (2025)
  Yu Zhang et al.
  7.13
• MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling (2025)
  Simon Rouard et al.
  7.08
• Listening And Seeing Again: Generative Error Correction For Audio-visual Speech Recognition (2025)
  Rui Liu, Hongyu Yuan, Haizhou Li
  6.92
• A Generative-First Neural Audio Autoencoder (2026)
  Jonah Casebeer et al.
  6.79
• EmoSteer-TTS: Fine-Grained and Training-Free Emotion-Controllable Text-to-Speech via Activation Steering (2025)
  Tianxin Xie et al.
  6.69
• TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling (2025)
  Yuancheng Wang et al.
  6.69
• DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding (2026)
  Jiaming Zhou et al.
  6.62
• MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners (2025)
  Fang-Duo Tsai et al.
  6.58
• AV-SyncBench: Decoupled Benchmarking of Temporal and Semantic Audio-Visual Synchronization (2026)
  Tianhong Zhou et al.
  6.52
• WildSpoof Challenge Evaluation Plan (2025)
  Yihan Wu et al.
  6.45
• Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing (2025)
  Zhedong Zhang et al.
  6.41
• SpeechWeave: Diverse Multilingual Synthetic Text & Audio Data Generation Pipeline for Training Text to Speech Models (2025)
  Karan Dua et al.
  6.23
• UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities (2025)
  Xuenan Xu et al.
  6.23
• TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment (2026)
  Trung Dang et al.
  6.19
• Multilingual Source Tracing of Speech Deepfakes: A First Benchmark (2025)
  Xi Xuan et al.
  6.18
• Live Music Models (2025)
  Lyria Team: Antoine Caillon et al.
  6.18
• CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis (2025)
  Chun Yat Wu et al.
  6.18
• Qwen2.5-Omni Technical Report (2025)
  Jin Xu et al.
  6.17
• ReaLJam: Real-Time Human-AI Music Jamming with Reinforcement Learning-Tuned Transformers (2025)
  Alexander Scarlatos et al.
  6.12
• AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder (2025)
  Samir Sadok et al.
  6.06
• Lightweight End-to-end Text-to-speech Synthesis for low resource on-device applications (2025)
  Biel Tura Vecino et al.
  6.01
• SpeakEasy: Enhancing Text-to-Speech Interactions for Expressive Content Creation (2025)
  Stephen Brade et al.
  5.96
• DarkStream: real-time speech anonymization with low latency (2025)
  Waris Quamer et al.
  5.93
• Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokens (2025)
  Pin-Jui Ku et al.
  5.93
• Semantic-VAE: Semantic-Alignment Latent Representation for Better Speech Synthesis (2025)
  Zhikang Niu et al.
  5.93
• Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling (2025)
  Ju-Chieh Chou et al.
  5.87
• TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching (2025)
  Wenxiang Guo et al.
  5.84
• Identity-based Patterns In Deep Convolutional Networks: Generative Adversarial Phonology And Reduplication (2020)
  Gašper Beguš
  5.84
• Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice (2025)
  Shanbo Cheng et al.
  5.82
• SoulX-Podcast: Towards Realistic Long-form Podcasts with Dialectal and Paralinguistic Diversity (2025)
  Hanke Xie et al.
  5.63
• Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data (2026)
  Thanathai Lertpetchpun et al.
  5.63
• Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations (2025)
  Xue Jiang et al.
  5.59
• The Singing Voice Conversion Challenge 2025: From Singer Identity Conversion To Singing Style Conversion (2025)
  Lester Phillip Violeta et al.
  5.57
• FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation (2025)
  Luca Della Libera et al.
  5.57