论文解读
Test Time Adaptation for Speech Emotion Recognition
语音情感识别 | 7.0/10
预训练
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
The 3rd Clarity Prediction Challenge: A Machine Learning Challenge for Hearing aid Speech Intelligibility Prediction
语音增强 | 7.5/10
论文解读
The Synergistic Role of Audio and Large Video-Language Model in Source-Free Video Domain Adaptation
领域适应 | 7.0/10
论文解读
Thinking While Listening: Simple Test Time Scaling for Audio Classification
音频分类 | 6.5/10
论文解读
Timbre-Based Pretraining with Pseudo-Labels for Multi-Instrument Automatic Music Transcription
音乐信息检索 | 7.0/10
论文解读
Tldiffgan: A Latent Diffusion-Gan Framework with Temporal Information Fusion for Anomalous Sound Detection
音频事件检测 | 7.5/10
论文解读
Tpeformer: Temporal Patch Embedding Transformer
语音情感识别 | 7.5/10
论文解读
Training-Free Inference-Time Scaling for Audio Source Separation
语音增强 | 7.5/10
论文解读
Tri-Attention Fusion: Joint Temporal-Spectral and Bidirectional Modeling for Speech Spoofing Detection
语音伪造检测 | 7.0/10
论文解读
WaveSP-Net: Learnable Wavelet-Domain Sparse Prompt Tuning for Speech Deepfake Detection
语音伪造检测 | 8.0/10
论文解读
WavLink: Compact Audio–Text Embeddings with a Global Whisper Token
音频检索 | 8.0/10
论文解读
An event-based sequence modeling approach to recognizing non-triad chords with oversegmentation minimization
音乐理解 | 7.5/10
论文解读
Scaling Properties of Continuous Diffusion Spoken Language Models
语音生成 | 8.0/10
论文解读
DiariZen Explained: A Tutorial for the Open Source State-of-the-Art Speaker Diarization Pipeline
说话人分离 | 6.5/10
论文解读
Misinformation Span Detection in Videos via Audio Transcripts
音频安全 | 7.5/10
论文解读
Environmental Sound Deepfake Detection Using Deep-Learning Framework
1. **问题**：针对环境声音（包括声音场景和声音事件）的深度伪造检测（ESDD）任务，现有研究不足，且尚不清楚声音场景与声音事件的伪造检测是否需要不同模型。 2. **方法核心**：提出一个深度学习框架，核心是采用预训练的音频模型（BEATs）作为特征提取器，并结合一种三阶段训练策略（包含对
论文解读
Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages
1. **问题**：现有针对基于神经音频编解码器的语音深度伪造（CodecFake）检测的研究主要集中在英语和中文，对于语言多样性极高的印度语言缺乏大规模的基准数据集和有效的检测方法。 2. **方法**：作者构建了首个大规模印度语言CodecFake数据集（ICF），并提出了一个名为SATYA
论文解读
MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation
这篇论文旨在解决语音到语音翻译（S2ST）系统普遍丢失源语音中非语言声音（如笑声、哭声）和情感信息的问题，这严重影响了跨语言交流的自然度和准确性。为此，作者提出了三项核心贡献：首先，设计了一个可扩展的自动化数据合成管道，用于生成大规模、高质量的英中富有表现力S2ST平行语料，克服了训练数据稀缺的瓶颈
论文解读
Environmental Sound Deepfake Detection Using Deep-Learning Framework
本文针对环境声音（如声音事件、声音场景）的深度伪造检测这一新兴任务，提出了一个系统的深度学习框架。**核心贡献**在于通过大量实验，系统评估了不同频谱图（MEL, CQT, Gammatone）、多种CNN架构（ResNet, Inception等）以及预训练模型（BEATs）在该任务上的表现，并验