论文解读
A Distribution Matching Approach to Neural Piano Transcription with Optimal Transport
音乐转录 | 5.5/10
最优传输
论文解读
Optimal Transport Audio Distance with Learned Riemannian Ground Metrics
音频质量评估 | 7.0/10
论文解读
Beyond Instance-Level Alignment: Dual-Level Optimal Transport for Audio-Text Retrieval
音频检索 | 7.5/10
论文解读
Beyond Instance-Level Alignment: Dual-Level Optimal Transport for Audio-Text Retrieval
音频检索 | 8.0/10
论文解读
A Distribution Matching Approach to Neural Piano Transcription with Optimal Transport
音乐转录 | 7.0/10
论文解读
BEST-STD 2.0: Balanced and Efficient Speech Tokenizer for Spoken Term Detection
音频检索 | 7.5/10
论文解读
Beyond Mapping: Domain-Invariant Representations via Spectral Embedding of Optimal Transport Plans
领域适应 | 7.5/10
论文解读
MCI-OTFusion: A Multimodal Model for MCI Detection and Cognitive Score Prediction
轻度认知障碍检测 | 6.5/10
论文解读
Prosody as Supervision: Bridging the Non-Verbal--Verbal for Multilingual Speech Emotion Recognition
这篇论文旨在解决低资源多语言语音情感识别（SER）中标注数据稀缺的核心瓶颈。作者提出了一个颠覆性的范式：**将SER重新定义为无监督的“非言语到言语”迁移问题**。其核心假设是，非言语发声（如笑、哭）中蕴含的韵律情感线索比言语更纯粹、更跨语言，因此可以作为更好的监督源。为此，作者设计了**NOVA-