论文解读
Optimizing Speech Language Models for Acoustic Consistency
语音合成 | 8.0/10
自监督学习
论文解读
Phonological Tokenizer: Prosody-Aware Phonetic Token Via Multi-Objective Fine-Tuning with Differentiable K-Means
语音表示学习 | 8.0/10
论文解读
Polynomial Mixing for Efficient Self-Supervised Speech Encoders
语音识别 | 8.0/10
论文解读
Position-Invariant Fine-Tuning Of Speech Enhancement Models With Self-Supervised Speech Representations
语音增强 | 6.5/10
论文解读
QE-XVC: Zero-Shot Cross-Lingual Voice Conversion via Query-Enhancement and Conditional Flow Matching
语音转换 | 7.5/10
论文解读
RASD-SR: A Robust Anomalous Sound Detection Framework with Score Recalibration
异常声音检测 | 8.5/10
论文解读
Reading Between the Waves: Robust Topic Segmentation Using Inter-Sentence Audio Features
音频分类 | 7.0/10
论文解读
Recovering Performance in Speech Emotion Recognition from Discrete Tokens Via Multi-Layer Fusion and Paralinguistic Feature Integration
语音情感识别 | 6.5/10
论文解读
Representation-Based Data Quality Audits for Audio
数据集 | 7.5/10
论文解读
Representation-Diverse Self-Supervision for Cross-Domain Bioacoustic Learning in Low-Resource Settings
生物声学 | 7.0/10
论文解读
Residual Tokens Enhance Masked Autoencoders for Speech Modeling
语音合成 | 7.0/10
论文解读
Robust Accent Identification via Voice Conversion and Non-Timbral Embeddings
语音识别 | 7.5/10
论文解读
Robust Deepfake Audio Detection via Multi-Level Intermediate Feature Fusion
音频深度伪造检测 | 7.5/10
论文解读
S-SONDO: Self-Supervised Knowledge Distillation for General Audio Foundation Models
音频分类 | 7.0/10
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
论文解读
Scaling Spoken Language Models with Syllabic Speech Tokenization
语音理解 | 7.0/10
论文解读
SED: Structural Entropy Based Speech Discretization for Discrete Token-Based ASR
语音识别 | 6.5/10
论文解读
Self-Supervised Note Tracking and Multi-Pitch Estimation Via Reconstruction-Based Learning
多音高估计 音符跟踪 | 8.5/10
论文解读
Sidon: Fast and Robust Open-Source Multilingual Speech Restoration for Large-Scale Dataset Cleansing
语音增强 | 8.5/10
论文解读
SingMOS-Pro: An Comprehensive Benchmark For Singing Quality Assessment
歌唱语音合成 | 7.5/10