论文解读
MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
基准测试 | 8.5/10
大语言模型
论文解读
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
多模态模型 | 7.5/10
论文解读
Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion
语音翻译 | 8.5/10
论文解读
Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences
语音识别 | 7.5/10
论文解读
TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICES
多模态模型 | 7.0/10
论文解读
Towards True Speech-to-Speech Models Without Text Guidance
语音对话系统 | 7.5/10
论文解读
UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice
语音翻译 | 8.0/10
论文解读
VowelPrompt: Hearing Speech Emotions from Text via Vowel-level Prosodic Augmentation
语音情感识别 | 8.5/10
每日研究速递
语音/音乐/音频论文速递 2026-05-03
共分析 13 篇语音/AI 论文
论文解读
AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
音视频 | 8.0/10
论文解读
Can Speech LLMs Think while Listening?
语音对话系统 | 7.5/10
论文解读
Closing the Gap Between Text and Speech Understanding in LLMs
语音对话系统 | 7.5/10
论文解读
Confident and Adaptive Generative Speech Recognition via Risk Control
语音识别 | 8.0/10
论文解读
DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations
语音对话系统 | 8.5/10
论文解读
Instilling an Active Mind in Avatars via Cognitive Simulation
数字人生成 | 8.0/10
论文解读
InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation?
基准测试 | 7.5/10
论文解读
LLM2Fx-Tools: Tool Calling for Music Post-Production
音乐信息检索 | 8.0/10
论文解读
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
音频问答 | 8.0/10
论文解读
Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis
音频分类 | 8.5/10
论文解读
Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion
语音翻译 | 8.0/10