论文解读
Beyond Generative Decoding: Discriminative Hidden-State Readout from a Native Omni-Modal LLM for Multimodal Sentiment Analysis
多模态模型 | 5.3/10
多模态模型
论文解读
Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models
音频问答 | 6.4/10
论文解读
Forgive or forget: Understanding the context of hate in audio retrieval systems
音频检索 | 7.4/10
论文解读
M2S-AVSR: Modality-aware Multi-view Self-supervised Representation for Robust Audio-Visual Speech Recognition
语音识别 | 9/10
论文解读
MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models
语音识别 | 8.4/10
论文解读
To Be Multimodal or Not to Be: Query-Adaptive Audio-Visual Person Retrieval via Active Modality Detection
说话人识别 | 6.8/10
每日研究速递
语音/音乐/音频论文速递 2026-06-05
共分析 47 篇语音/AI 论文
论文解读
DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities
多模态模型 | 9.3/10
论文解读
Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention
语音问答 | 7.5/10
论文解读
Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026
语音识别 | 10/10
每日研究速递
语音/音乐/音频论文速递 2026-06-04
共分析 22 篇语音/AI 论文
论文解读
A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026
语音翻译 | 6.8/10
论文解读
Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals
语音情感识别 | 7.2/10
论文解读
Benchmarking Speech-to-Speech Translation Models
语音合成 | 8.7/10
论文解读
Cosmos 3: Omnimodal World Models for Physical AI
音频生成 | 10/10
论文解读
Foley-Omni: A Unified Multimodal Generation Model from Task-Level Audio Synthesis to Complete Video Soundtrack Generation
音频生成 | 7/10
论文解读
MoDAl: Self-Supervised Neural Modality Discovery via Decorrelation for Speech Neuroprosthesis
自监督学习 | 6.6/10
论文解读
OmniHalluc-L: Counterfactual Benchmarking and Modality-Perturbation Reliability Calibration for Long-Form Omni Hallucination
多模态模型 | 7.8/10
论文解读
SegTune: Structured and Fine-Grained Control for Song Generation
音乐生成 | 8.5/10
论文解读
SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling
音乐生成 | 8.6/10