论文解读
ASR 评测别急着换大模型：先分清向量度量、候选裁判与错误解释
语音质量评估 | 6.1/10
大语言模型
论文解读
谐音不是错字：让普通话 ASR 在纠错与保留笑点之间踩刹车
语音识别 | 5.7/10
论文解读
语音助手的记忆为什么要分脑：VoiceMem 用 134 ms 换来 top-5 的长期理解
语音交互 | 6.6/10
论文解读
Benchmarking LLM Judges for Voice-Agent Evaluation: Reliability, Calibration, and Human Oversight
语音交互 | 6.6/10
论文解读
Better Retrieval, Worse Robustness: How Multi-hop RAG Amplifies Upstream ASR Errors
音频理解 | 9.1/10
论文解读
Development and Feasibility Evaluation of an Edge AI as Medical Device System for Breast Cancer Multidisciplinary Team Meetings
语音识别 | 8.4/10
论文解读
Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Recommendation
音乐推荐 | 8.3/10
论文解读
Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does
语音交互 | 6.4/10
论文解读
MultiVerse: A Creator-Centered Approach to Steering Context-Adaptive Lyrics
音乐生成 | 5.4/10
论文解读
Represented but Ignored: A Causal Account of Prosodic Underuse in Audio-Language Models
音频理解 | 7.2/10
每日研究速递
语音/音乐/音频论文速递 2026-08-21
共分析 18 篇语音/AI 论文
论文解读
Accurate Decoding of Natural Sentences from Non-Invasive Brain Recordings
语音识别 | 7.5/10
论文解读
Large Language Models in Mental Health: A Systematic Review of Applications, Innovations, and Ethical Challenges
多模态模型 | 6.0/10
论文解读
Pedagogical AI in Mental Health: A Tri-Stream Fine-Tuned LLM Framework for Automated Clinical Supervision and Risk Triage
多模态模型 | 6.7/10
论文解读
StocksTalk: A Voice-Enabled Conversational Agent for Structured Query Generation over Web Data
语音交互 | 6.7/10
每日研究速递
语音/音乐/音频论文速递 2026-08-20
共分析 20 篇语音/AI 论文
论文解读
PolyDebate: A Game-Orchestrated Multimodal System for Debate Skills Practice and Evaluation
语音交互 | 6.8/10
论文解读
Why GPT-Style Models Do Not Directly Transfer to Symbolic Music: Compression in the Wrong Coordinate System
音乐生成 | 6.7/10
每日研究速递
语音/音乐/音频论文速递 2026-08-19
共分析 16 篇语音/AI 论文
论文解读
Cached LLM Probability Retrieval for Speech Recognition
语音识别 | 6.1/10