论文解读
DynaForcing: Overcoming Dynamic Collapse in Self-Forcing Distillation for Streaming Avatar Generation
音视频生成 | 8.0/10
Posts
论文解读
Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models
音视频理解 | 7.4/10
论文解读
FireRedTTS3: Unified Speech Generation and Editing with Semantically Enriched Speech Representations
语音合成 | 9.0/10
论文解读
Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges
语音交互 | 6.5/10
论文解读
On computational approaches to Pop music culture
音乐理解 | 6.1/10
论文解读
PolyDebate: A Game-Orchestrated Multimodal System for Debate Skills Practice and Evaluation
语音交互 | 6.8/10
论文解读
SpeechSense: A Paralinguistic-Focused Dataset for Fine-Grained Speech Sentiment Analysis
语音情感识别 | 8.5/10
论文解读
Target Speaker Identification: A Low-Latency Streaming Pipeline
说话人验证 | 5.6/10
论文解读
The Last Mile of Deepfake Speech Detection: An Industry-Academia Experience Report
语音伪造检测 | 6.6/10
论文解读
Uncertainty-Aware Decision Making in Multimodal Large Language Models
音频理解 | 6.8/10
论文解读
UniVerse: Benchmarking and Enhancing LALMs on Culturally Inclusive Low-Resource Music Understanding
音乐理解 | 7.1/10
论文解读
Why GPT-Style Models Do Not Directly Transfer to Symbolic Music: Compression in the Wrong Coordinate System
音乐生成 | 6.7/10
每日研究速递
语音/音乐/音频论文速递 2026-08-19
共分析 16 篇语音/AI 论文
论文解读
A Novel Binaural Cue Preservation Loss for DNN-Based Binaural Speech Enhancement
语音增强 | 5.6/10
论文解读
A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification
音频分类 | 5.9/10
论文解读
A survey of AI-generated voices and their detection
语音伪造检测 | 6.1/10
论文解读
ACE-Cap: Active Evidence Acquisition via Agentic Co-Evolution for Long-Paragraph Fine-Grained Audio Captioning
音频字幕生成 | 7.5/10
论文解读
Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer
语音克隆 | 6.4/10
论文解读
An Analytical-Prior Framework for Data-Efficient Prediction of Sound-Reduction Frequencies in Rectangular Side-Branch Helmholtz Resonators
预训练 | 5.8/10
论文解读
AnyTalk: Speech Animation for Arbitrary Characters Leveraging a Video Generation Model
音视频语音合成 | 6.7/10