{"total":94,"rows":[{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"area":null},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"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":"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":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"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":"2502.04465","title":"FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks","created":"2025-02-06","cited_by_count":18,"area":null},{"id":"2508.05835","title":"NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference","created":"2025-08-07","cited_by_count":15,"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":"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":"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":"2509.16195","title":"FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation","created":"2025-09-19","cited_by_count":9,"area":null},{"id":"2510.04577","title":"Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers","created":"2025-10-06","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":"2503.04724","title":"LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM","created":"2025-03-06","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":"2505.14470","title":"PAST: Phonetic-Acoustic Speech Tokenizer","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2601.01373","title":"UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2412.16846","title":"KALL-E:Autoregressive Speech Synthesis with Next-Distribution Prediction","created":"2024-12-22","cited_by_count":5,"area":null},{"id":"2412.19128","title":"Semantic Residual for Multimodal Unified Discrete Representation","created":"2024-12-26","cited_by_count":5,"area":null},{"id":"2505.23494","title":"Spoken Language Modeling with Duration-Penalized Self-Supervised Units","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2508.02849","title":"SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codec","created":"2025-08-04","cited_by_count":5,"area":null},{"id":"2511.13300","title":"PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement","created":"2025-11-17","cited_by_count":5,"area":null},{"id":"2602.07064","title":"OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization","created":"2026-02-05","cited_by_count":5,"area":null},{"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":"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":"2508.17863","title":"Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs","created":"2025-08-25","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":"2602.19574","title":"CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment","created":"2026-02-23","cited_by_count":3,"area":null},{"id":"2609.08977","title":"Multimodal Duplex Interaction Agent","created":"2026-09-08","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":"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":"2509.07526","title":"Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2510.12834","title":"Gelina: Unified Speech and Gesture Synthesis via Interleaved Token Prediction","created":"2025-10-13","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":"2601.17761","title":"AR-Omni: A Unified Autoregressive Model for Any-to-Any Generation","created":"2026-01-25","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":"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":"2605.05927","title":"Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.29948","title":"HoliTok: A Continuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2609.22452","title":"Vox-Infinity: Benchmarking the Limits of Long-Context Spoken Language Models","created":"2026-09-18","cited_by_count":2,"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":"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":"2506.12537","title":"What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study","created":"2025-06-14","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":"2507.12825","title":"Autoregressive Speech Enhancement via Acoustic Tokens","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2509.03526","title":"Enhancing Speech Large Language Models through Reinforced Behavior Alignment","created":"2025-08-25","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":"2509.26276","title":"Optimizing Speech Language Models for Acoustic Consistency","created":"2025-09-30","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":"2602.15491","title":"The Equalizer: Introducing Shape-Gain Decomposition in Neural Audio Codecs","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.12350","title":"TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.01832","title":"GAP-URGENet: A Generative-Predictive Fusion Framework for Universal Speech Enhancement","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2605.01790","title":"Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2605.11192","title":"Exploring Token-Space Manipulation in Latent Audio Tokenizers","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.20519","title":"Codec-Robust Attacks on Audio LLMs","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.29488","title":"AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.13630","title":"From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.30811","title":"AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation","created":"2026-06-29","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":"2412.13917","title":"Speech Watermarking with Discrete Intermediate Representations","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2504.00561","title":"Continual Cross-Modal Generalization","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2504.03289","title":"RWKVTTS: Yet another TTS based on RWKV-7","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2505.17076","title":"Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2507.06802","title":"Speech Tokenizer is Key to Consistent Representation","created":"2025-07-09","cited_by_count":0,"area":null},{"id":"2509.11425","title":"FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2511.20224","title":"DuoTok: Source-Aware Dual-Track Music Tokenization for Vocal-Accompaniment Generation","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2601.20185","title":"Improving X-Codec-2.0 for Multi-Lingual Speech: 25 Hz Latent Rate and 24 kHz Sampling","created":"2026-01-28","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":"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":"2605.06870","title":"Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.29219","title":"SalsaAgent: A multimodal embodied language model for interactive dance generation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.31521","title":"UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.02631","title":"Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals","created":"2026-05-30","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":"2606.04418","title":"CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding","created":"2026-06-03","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":"2606.16969","title":"Probing Low Frame Rate Degradation in Neural Audio Codecs","created":"2026-06-15","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":"2607.14474","title":"Can Tokens Compete? Token Representations against Supervised CNN Backbones for BirdCLEF+ 2026","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.29363","title":"Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.05727","title":"LILAC: An Idempotent Neural Speech Codec","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.05871","title":"Where Does the Sound Go? Tracing Acoustic Information Loss in Audio-Conditioned LLMs","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.09719","title":"StreamAlign: Streaming Text-Aligned Speech Tokenization","created":"2026-09-09","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":"2609.22851","title":"Discrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.27382","title":"When Entanglement Lower-Bounds Disparity: Auditing and Repairing Demographic Fairness in Audio Understanding Models","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.32755","title":"SAGE: Semantic Audio Generative Encoder","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.00154","title":"How Robust Are Neural Audio Codecs for African Speech? A Multi-Task Benchmark and the Limits of Perceptual Quality","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2610.01492","title":"Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization","created":"2026-10-01","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}],"next_cursor":null}