{"total":44,"rows":[{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2601.15621","title":"Qwen3-TTS Technical Report","created":"2026-01-22","cited_by_count":118,"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":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2508.19205","title":"VibeVoice Technical Report","created":"2025-08-26","cited_by_count":29,"area":null},{"id":"2603.18090","title":"MOSS-TTS Technical Report","created":"2026-03-18","cited_by_count":14,"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":"2506.02863","title":"CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2512.13674","title":"Towards Interactive Intelligence for Digital Humans","created":"2025-12-15","cited_by_count":10,"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":"2509.18004","title":"WenetSpeech-Chuan: A Large-Scale Sichuanese Corpus with Rich Annotation for Dialectal Speech Processing","created":"2025-09-22","cited_by_count":8,"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":"2509.15969","title":"VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2506.02742","title":"Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2510.20441","title":"UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement","created":"2025-10-23","cited_by_count":4,"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":"2507.21138","title":"TTS-1 Technical Report","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2510.00499","title":"MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2505.17426","title":"UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information","created":"2025-05-23","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":"2510.02187","title":"High-Fidelity Speech Enhancement via Discrete Audio Tokens","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2601.02776","title":"UniSRCodec: Unified and Low-Bitrate Single Codebook Codec with Sub-Band Reconstruction","created":"2026-01-06","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":"2603.05887","title":"Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2603.19739","title":"MOSS-TTSD: Text to Spoken Dialogue Generation","created":"2026-03-20","cited_by_count":2,"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":"2509.19852","title":"Eliminating stability hallucinations in llm-based tts models via attention guidance","created":"2025-09-24","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":"2601.15596","title":"DeepASMR: LLM-Based Zero-Shot ASMR Speech Generation for Anyone of Any Voice","created":"2026-01-22","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":"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":"2509.15666","title":"TISDiSS: A Training-Time and Inference-Time Scalable Framework for Discriminative Source Separation","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2510.19414","title":"EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection","created":"2025-10-22","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":"2512.11480","title":"CADMorph: Geometry-Driven Parametric CAD Editing via a Plan-Generate-Verify Loop","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2602.16343","title":"How to Label Resynthesized Audio: The Dual Role of Neural Audio Codecs in Audio Deepfake Detection","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2605.14555","title":"Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.02739","title":"EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement","created":"2026-06-01","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":"2607.02633","title":"GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech","created":"2026-07-02","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":"2609.11642","title":"ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.25411","title":"Learnable Classifier-Free Guidance Null Embeddings for Enhanced Controllable Speech Synthesis","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.36974","title":"Repetition, Not Length: Isolating the Counting Failure in Neural Text-to-Speech","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}