论文解读
DETECT-3B-Omni is Agnostic of Content and Demographics
语音伪造检测 | 4.2/10
Posts
论文解读
Doppelganger: Sound Effects and Their Synthetic Twins
音频检索 | 9.1/10
论文解读
DuplexChat: Constructing Speaker-Separated Full-Duplex Dialogue Speech at Scale for Spoken Dialogue Language Modeling
语音交互 | 5.9/10
论文解读
Evaluating the Effect of Linguistic Relatedness on Cross-Lingual Transfer in Large Multilingual Automatic Speech Recognition
语音识别 | 6.5/10
论文解读
Information-Geometric Superposed Vowel Evaluation: Part 1. Moraic Syllabary (Japanese)
语音伪造检测 | 1.9/10
论文解读
Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion
语音识别 | 5.8/10
论文解读
Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment
语音情感识别 | 5.5/10
论文解读
Lights, Camera, Carbon: Architectural Scaling Laws for Video Generation Energy Consumption
音视频生成 | 6.9/10
论文解读
Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR
语音识别 | 7.5/10
论文解读
Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving
语音交互 | 8.7/10
论文解读
Mixture-Constrained Max Pooling Improves Separation-Based Bird Species Classification
音频分类 | 5.3/10
论文解读
MOSAIC: Interpretable Multi-Token Cross-Attention of Biophonetic and Self-Supervised Representations for Unified Voice Anti-Spoofing
语音伪造检测 | 6.3/10
论文解读
Noisy Environment Adaptation of Neural Speech Codec via Focal Mask and Noise Feature Separation
语音增强 | 5.9/10
论文解读
NouveauVoice: Generating Novel Pseudo Speakers for Voice Anonymization
语音转换 | 5.9/10
论文解读
OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models
音视频问答 | 5.9/10
论文解读
Open-Set Source Tracing as Compositional Factors via Structured Prototypes
语音伪造检测 | 6/10
论文解读
Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning
音视频理解 | 8/10
论文解读
Physics-Informed Direction-of-Arrival Estimation Over Distributed Edge Devices
声源定位 | 5.3/10
论文解读
Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech
语音识别 | 6/10
论文解读
Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings
音频理解 | 6.2/10