论文解读
Unlocking Speech–Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
语音交互 | 6.7/10
Posts
论文解读
V-LynX: Token Interface Alignment for Video+X LLMs
音视频问答 | 7.8/10
论文解读
VIBE: Disentangling Social Dynamics via Kinematics-Informed Variational Inference for Behavioral Emotion
VIBE: Disentangling Social Dynamics via Kinematics-Informed Variational Inference for Behavioral Emotion
论文解读
video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
音视频问答 | 7.3/10
论文解读
VocSim A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio
音频检索 | 8.2/10
论文解读
WaveSSM: Multiscale State-Space Models for Non-stationary Signal Attention
音频分类 | 4.8/10
论文解读
Zero-Shot Rankability: Revealing Latent Ordinal Structure in Multimodal Large Language Models via Language
音视频理解 | 6.8/10
论文解读
A global predicted-fMRI drive signal from TRIBE does not predict YouTube replay heatmaps
音视频理解 | 7.7/10
论文解读
A Multi-Branch Hierarchy-Aware Framework for Heterogeneous Audio Classification
音频分类 | 4.9/10
论文解读
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation
语音合成 | 6.8/10
论文解读
Audio-Based Understanding of Audiobook Narration Appeal
语音属性识别 | 6.9/10
论文解读
Beyond Words: Towards Effective Modeling of Non-Verbal Vocalizations in ASR
语音识别 | 6.4/10
论文解读
CNN Models for Microphone Array Covariance Matrix Upsampling and Acoustic Imaging
声源定位 | 5/10
论文解读
Cross Domain Few-Shot Class-Incremental Audio Classification Via Adversarial Contrastive Learning
音频分类 | 7.4/10
论文解读
Decomposer: Learning to Decompile Symbolic Music to Programs
音乐理解 | 8.4/10
论文解读
DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning
音频分类 | 4.7/10
论文解读
Enhancing Acoustic-to-Articulatory Inversion with Multi-Target Pretraining for Low-Resource Settings
语音交互 | 7/10
论文解读
Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes
音频分类 | 6.8/10
论文解读
From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languages
语音识别 | 4.8/10
论文解读
H-SAGE: Holistic Speaker-Aware Guided Experts for MoE-based Multi-Talker ASR
语音识别 | 6.9/10