论文解读
CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition
语音识别 | 8.0/10
开源工具
论文解读
Deep Learning with Learnable Product-Structured Activations
音频分类 | 7.5/10
论文解读
DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick
语音编码 | 8.5/10
论文解读
Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
音频场景理解 | 9.0/10
论文解读
OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
多模态模型 | 8.0/10
论文解读
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization
音频生成 | 8.5/10
论文解读
TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICES
多模态模型 | 7.0/10
论文解读
Audio Video Verbal Analysis (AVVA) for Capturing Classroom Dialogues
音频问答 | 6.0/10
论文解读
MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents
模型评估 | 7.5/10
论文解读
TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis
语音质量评估 | 7.5/10
论文解读
Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost
语音合成 | 8.0/10
论文解读
A Text-To-Text Alignment Algorithm for Better Evaluation of Modern Speech Recognition Systems
模型评估 | 7.5/10
论文解读
Constructing Composite Features for Interpretable Music-Tagging
音乐信息检索 | 7.5/10
论文解读
Denoising Of Stochastic Ray Tracing Room Impulse Responses
空间音频 | 7.5/10
论文解读
ECHO: Frequency-Aware Hierarchical Encoding for Variable-Length Signals
音频分类 | 9.5/10
论文解读
Evaluating High-Resolution Piano Sustain Pedal Depth Estimation with Musically Informed Metrics
音乐信息检索 | 8.0/10
论文解读
MNV-17: A High-Quality Performative Mandarin Dataset for Nonverbal Vocalization Recognition in Speech
语音识别 | 7.5/10
论文解读
Polynomial Mixing for Efficient Self-Supervised Speech Encoders
语音识别 | 8.0/10
论文解读
Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost
语音合成 | 8.0/10
论文解读
SA-SSL-MOS: Self-Supervised Learning MOS Prediction with Spectral Augmentation for Generalized Multi-Rate Speech Assessment
语音质量评估 | 7.0/10