论文解读
Proficiency-Aware Adaptation and Data Augmentation for Robust L2 ASR
语音识别 | 6.5/10
多任务学习
论文解读
PROST-LLM: Progressively Enhancing the Speech-to-Speech Translation Capability in LLMs
语音翻译 | 7.5/10
论文解读
Purification Before Fusion: Toward Mask-Free Speech Enhancement for Robust Audio-Visual Speech Recognition
语音识别 | 7.5/10
论文解读
Reference-Aware SFM Layers for Intrusive Intelligibility Prediction
语音评估 | 7.5/10
论文解读
SEP-ST: Incorporating Speech Entity Prompt Into Large Language Models for Speech Translation
语音翻译 | 7.5/10
论文解读
Session-Level Spoken Language Assessment with A Multimodal Foundation Model Via Multi-Target Learning
语音评估 | 7.5/10
论文解读
Shared Representation Learning for Reference-Guided Targeted Sound Detection
音频事件检测 | 8.5/10
论文解读
Stress Prediction from Temporal Emotion Trajectories in Clinical Patient-Physician Conversations
语音情感识别 | 7.0/10
论文解读
Task-Oriented Sound Privacy Preservation for Sound Event Detection Via End-to-End Adversarial Multi-Task Learning
音频事件检测 | 7.5/10
论文解读
Text2Move: Text-To-Moving Sound Generation via Trajectory Prediction and Temporal Alignment
空间音频 | 8.0/10
论文解读
Tokenchain: A Discrete Speech Chain via Semantic Token Modeling
语音识别 | 7.0/10
论文解读
Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages
语音识别 | 6.5/10
论文解读
Transfer Learning for Paediatric Sleep Apnoea Detection using Physiology-Guided Acoustic Models
音频分类 | 7.0/10
论文解读
Triad: Tri-Head with Auxiliary Duplicating Permutation Invariant Training for Multi-Task Sound Event Localization and Detection
音频事件检测 | 7.5/10
论文解读
TTA: Transcribe, Translate and Alignment for Cross-Lingual Speech Representation
语音识别 | 7.5/10
论文解读
Vioptt: Violin Technique-Aware Transcription from Synthetic Data Augmentation
音乐信息检索 | 6.5/10
论文解读
Whisper-FEST: Single-Channel Far-Field Enhanced Speech-to-text without Parallel Data
语音识别 | 7.5/10
论文解读
Whisper-QF: Leveraging Dual Cross-Attention Q-Former for Speech Emotion Recognition With Multi-Task Learning
语音情感识别 | 7.5/10
每日研究速递
语音/音乐/音频论文速递 2026-04-29
共分析 29 篇语音/AI 论文
论文解读
Explicit Dropout: Deterministic Regularization for Transformer Architectures
这篇论文旨在解决传统Dropout方法依赖随机掩码、正则化效果不透明且难以精确控制的问题。其核心方法是提出一种确定性公式，将Dropout重新表述为一个可直接加入训练损失函数的显式正则化项，并推导出了适用于Transformer架构中注意力机制（Q、K、V）和前馈网络的正则化表达式。与已有方法相比，