{"total":118,"rows":[{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165,"area":"wm"},{"id":"2607.05369","title":"GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks","created":"2026-07-06","cited_by_count":14,"area":"agents"},{"id":"2606.01802","title":"MOSS-Audio Technical Report","created":"2026-06-01","cited_by_count":11,"area":null},{"id":"2604.08000","title":"PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory","created":"2026-04-09","cited_by_count":9,"area":null},{"id":"2605.23912","title":"Raon-Speech Technical Report","created":"2026-04-08","cited_by_count":7,"area":null},{"id":"2603.11123","title":"Uni-ASR: Unified LLM-Based Architecture for Non-Streaming and Streaming Automatic Speech Recognition","created":"2026-03-11","cited_by_count":6,"area":null},{"id":"2604.00007","title":"Dynin-Omni: Omnimodal Unified Large Diffusion Language Model","created":"2026-03-09","cited_by_count":5,"area":"diffusion"},{"id":"2605.19833","title":"Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation","created":"2026-05-19","cited_by_count":5,"area":null},{"id":"2604.06138","title":"Generating Synthetic Doctor-Patient Conversations for Long-form Audio Summarization","created":"2026-04-07","cited_by_count":4,"area":null},{"id":"2606.05121","title":"Audio Interaction Model","created":"2026-06-03","cited_by_count":4,"area":null},{"id":"2603.06193","title":"Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding","created":"2026-03-06","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":"2608.10878","title":"X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction","created":"2026-08-11","cited_by_count":3,"area":null},{"id":"2604.23586","title":"Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling","created":"2026-04-26","cited_by_count":2,"area":"diffusion"},{"id":"2605.29430","title":"Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2606.05917","title":"MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering","created":"2026-06-04","cited_by_count":2,"area":"mllm"},{"id":"2608.26005","title":"VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction","created":"2026-08-26","cited_by_count":2,"area":null},{"id":"2603.05354","title":"Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASR","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.21478","title":"TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.06191","title":"Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.08003","title":"Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2604.09121","title":"Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition","created":"2026-04-10","cited_by_count":1,"area":"agents"},{"id":"2604.18105","title":"NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.23935","title":"2nd of the 5th PVUW MeViS-Audio Track: ASR-SaSaSa2VA","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2604.26031","title":"Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2605.02782","title":"When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.08961","title":"Dolphin-CN-Dialect: Where Chinese Dialects Matter","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.19266","title":"FormalASR: End-to-End Spoken Chinese to Formal Text","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.00507","title":"LaSR: Context-Aware Speech Recognition via Latent Reasoning","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2606.06211","title":"FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.22811","title":"Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2606.31722","title":"Adapting Foundation ASR Models to Dysarthric Speech: A Case Study","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.10287","title":"InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2607.28175","title":"AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approach","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.03610","title":"Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR","created":"2026-08-04","cited_by_count":1,"area":"distill"},{"id":"2608.05759","title":"How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMs","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2609.08936","title":"AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.12872","title":"DuplexDrama: A Synthesized Dialogue Dataset with Scenarios, Full-Duplex Behaviors, Expressive Speech, and Sound Events","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2609.15759","title":"Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2609.23417","title":"Omni2Web: Benchmarking Audiovisual Website Development","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2609.23462","title":"Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2604.16056","title":"AST: Adaptive, Seamless, and Training-Free Precise Speech Editing","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.18932","title":"Tadabur: A Large-Scale Quran Audio Dataset","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2604.27543","title":"AppTek Call-Center Dialogues: A Multi-Accent Long-Form Benchmark for English ASR","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.04613","title":"VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Models","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.23954","title":"EchoDistill: Robust Large Audio Language Models via Noisy-to-Clean Self-Distillation","created":"2026-05-11","cited_by_count":0,"area":"distill"},{"id":"2605.27258","title":"PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.31173","title":"MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.04680","title":"Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.17126","title":"Vibrato Expression Control for Singing Voice Conversion with Improving Independent Control","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.17826","title":"When Multiple Scripts Matter: Evaluating ASR in Clinical Settings","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.19203","title":"DASH: Dual-View Self-Distillation with Multi-Layer Hidden Representations for Robust Speech Recognition","created":"2026-06-17","cited_by_count":0,"area":"distill"},{"id":"2606.27717","title":"Do Speech Emphasis Models Generalize across Languages and Emotions?","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.01733","title":"Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.08208","title":"Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.08409","title":"When Synthetic Speech Is All You Have: Better Call GRPO","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2607.27768","title":"VocalRender: Score-Native Singing Voice Synthesis for Real-World Composition","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.04479","title":"AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.09475","title":"Agreement-Based Audio-Visual Segmentation:Champion Report for the MeViS-Audio Track in the 8th LSVOS Challenge","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.10606","title":"ASR-Roundtrip Evaluation Can Mask Context- and Convention-Dependent Reading Errors in Chinese News TTS","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.10836","title":"Whisper-Aware LLM: Self-Supervised Uncertainty Learning for Robust Whispered Speech Recognition","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.11898","title":"On-Policy Self-Distillation for Multi-Dialect ASR: Mastering Dialects, Retaining Mandarin","created":"2026-08-12","cited_by_count":0,"area":"distill"},{"id":"2608.14870","title":"JarvisBench: Always-on Intelligence Between Humans and Agents","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.19936","title":"Towards Quantifying Benchmark Optimization in ASR Models","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.23234","title":"MLLM-Assisted Audio VOS: A 3rd Place Report for the MeViS-Audio Track, 8th LSVOS Challenge","created":"2026-08-24","cited_by_count":0,"area":"mllm"},{"id":"2608.28699","title":"Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2608.31106","title":"DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.02901","title":"Dual-Form ASR: Semantics-Aware Inverse Text Normalization for Chinese Speech Recognition","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.06078","title":"Report of the 8th LSVOS Challenge: Complex and Multimodal Video Object Segmentation","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.08672","title":"X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.09677","title":"X2-NativeCursor: Native-Token Text Progress Tracking for Incremental-Text Streaming Codec TTS","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.09852","title":"$S^3$-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants","created":"2026-09-09","cited_by_count":0,"area":"mllm"},{"id":"2609.11786","title":"Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.12122","title":"Quantifying Consonant Contributions to Word Intelligibility via Acoustic Masking","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.12623","title":"SteerDuplex: Steerable Duplex Speech Dialogue Models","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.14467","title":"Bridging the Modality Gap in Long-Form Clinical Audio: A Comparative Study of Lightweight and Heavyweight End-to-End SOAP Generation","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.18333","title":"Look Less, Hear Better: Jointly Rewarded GRPO for Streaming ASR","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.18521","title":"VoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.18677","title":"Voice of Reason: Reinforcement Learning for Spoken Math","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2609.18680","title":"HearInContext: A Benchmark for Implicit Context in Speech Recognition","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.20104","title":"Design of the IBM Granite 5.0 TurboCTC ASR Model","created":"2026-09-17","cited_by_count":0,"area":"inference"},{"id":"2609.20833","title":"Transsion's Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2609.21465","title":"OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.22214","title":"The Bairong System for MLC-SLM 2026: Dynamic Question-Aware Evidence Routing for Multilingual Conversational Speech Understanding","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.22697","title":"COT-TTS: Audio Context-Aware Text-to-Speech with Chain-of-Thought Reasoning","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"id":"2609.27289","title":"Ruby-ASR: Evidence-Preserving Supervision for Joint Orthographic and Lexical-Reading Recognition","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.28437","title":"MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.28727","title":"PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMs","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.28806","title":"A Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.29428","title":"agentic-ger: terminology recovery in long-form speech using global context","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.29800","title":"Adaptive Fisher-Whitened Cross-Covariance for Low-Resource Speech Recognition","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30469","title":"Pretrained ASR Pseudo-labeling for Noisy Police Audio","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.31652","title":"Open-Qwen-Music: An Auditable Framework for LLM-Based Music Composition and Diffusion Rendering","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.32396","title":"FA-Bench: A Benchmark for Phone- and Word-Level Timestamp Accuracy in Forced Alignment and ASR on Clean and Noisy Speech","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33245","title":"Acoustic Progress Propagation for Long-Horizon Speculative Decoding in ASR","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2609.33362","title":"From Script to Drama: An Agentic Framework for Controllable Multi-Speaker Dialogue TTS","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.33443","title":"Context Spanning: A Communication Framework for Full-Duplex Speech Models and External LLM Backends","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33650","title":"FuseAlign: Forced Alignment in the Wild","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33757","title":"YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33810","title":"Controlling Speaking Rate in Autoregressive TTS via Activation Steering","created":"2026-09-27","cited_by_count":0,"area":"mechinterp"}],"next_cursor":"100"}