论文解读
UALM: Unified Audio Language Model for Understanding, Generation and Reasoning
音频生成 | 8.5/10
音频大模型
论文解读
Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding
音频场景理解 | 8.0/10
论文解读
A Generative-First Neural Audio Autoencoder
音乐生成 | 8.5/10
论文解读
AR&D: A Framework for Retrieving and Describing Concepts for Interpreting AudioLLMs
音频大模型 | 6.5/10
论文解读
Auditory Illusion Benchmark for Large Audio Language Models
模型评估 | 7.0/10
论文解读
Can Large Audio Language Models Understand Audio Well? Speech, Scene and Events Understanding Benchmark for LALMs
基准测试 | 7.0/10
论文解读
Deepaq: A Perceptual Audio Quality Metric Based on Foundational Models and Weakly Supervised Learning
音频质量评估 | 7.5/10
论文解读
DisContSE: Single-Step Diffusion Speech Enhancement based on Joint Discrete and Continuous Embeddings
语音增强 | 8.5/10
论文解读
DSpAST: Disentangled Representations for Spatial Audio Reasoning with Large Language Models
音频问答 | 8.0/10
论文解读
ECHO: Frequency-Aware Hierarchical Encoding for Variable-Length Signals
音频分类 | 9.5/10
论文解读
Emo-TTA: Improving Test-Time Adaptation of Audio-Language Models for Speech Emotion Recognition
语音情感识别 | 7.0/10
论文解读
Emotional Damage: Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations
音频安全 | 7.5/10
论文解读
Evaluating Compositional Structure in Audio Representations
模型评估 | 7.0/10
论文解读
Exploring How Audio Effects Alter Emotion with Foundation Models
音乐理解 | 7.0/10
论文解读
From Contrast to Commonality: Audio Commonality Captioning for Enhanced Audio-Text Cross-Modal Understanding in Multimodal LLMS
音频场景理解 | 7.5/10
会议任务专题
ICASSP 2026 - 音频大模型
共 1 篇 ICASSP 2026 音频大模型 方向论文
论文解读
Improving Audio Question Answering with Variational Inference
音频问答 | 7.5/10
论文解读
Investigating Modality Contribution in Audio LLMs for Music
模型评估 | 6.5/10
论文解读
Keeping Models Listening: Segment- and time-aware attention rescaling at decoding time
音频问答 | 7.5/10
论文解读
Modeling Inter-Segment Relationships in Speech for Dementia Detection with Audio Spectrogram Transformers and Graph Attention Networks
语音生物标志物 | 7.0/10