论文解读
Entropy-Guided GRVQ for Ultra-Low Bitrate Neural Speech Codec
语音合成 | 7.5/10
低资源
论文解读
Exploring Fine-Tuning Of Large Audio Language Models For Spoken Language Understanding Under Limited Speech Data
语音理解 | 8.0/10
论文解读
Fast-ULCNet: A Fast and Ultra Low Complexity Network for Single-Channel Speech Enhancement
语音增强 | 7.5/10
论文解读
FinHuBERT: Hierarchical Feature Imitating Networks for Low-Resource Speech Recognition
语音识别 | 7.5/10
论文解读
FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation
语音编码 | 8.0/10
论文解读
From Hallucination to Articulation: Language Model-Driven Losses for Ultra Low-Bitrate Neural Speech Coding
语音合成 | 7.5/10
论文解读
H-nnPBFDAF: Hierarchical Neural Network Partitioned Block Frequency Domain Adaptive Filter with Novel Block Activation Probability
语音增强 | 7.5/10
论文解读
HCGAN: Harmonic-Coupled Generative Adversarial Network for Speech Super-Resolution in Low-Bandwidth Scenarios
语音增强 | 8.0/10
论文解读
How Far Do SSL Speech Models Listen for Tone? Temporal Focus of Tone Representation under Low-Resource Transfer
语音识别 | 6.5/10
论文解读
Hybrid Pruning: In-Situ Compression of Self-Supervised Speech Models for Speaker Verification and Anti-Spoofing
说话人验证 | 8.0/10
论文解读
Improving Audio Event Recognition with Consistency Regularization
音频事件检测 | 7.0/10
论文解读
Leveraging Diffusion U-Net Features for Predominant Instrument Recognition
音乐信息检索 | 8.0/10
论文解读
Lightweight and Perceptually-Guided Voice Conversion for Electro-Laryngeal Speech
语音转换 | 7.5/10
论文解读
Lingometer: On-Device Personal Speech Word Counting System
语音活动检测 | 8.0/10
论文解读
LLM-Based Post-ASR Error Correction for Disordered Speech
语音识别 | 7.5/10
论文解读
LOTUSDIS: A Thai Far-Field Meeting Corpus for Robust Conversational ASR
语音识别 | 7.5/10
论文解读
Low-Resource Speech-Based Early Alzheimers Detection via Cross-Lingual and Few-Shot Transfer Learning
语音生物标志物 | 7.5/10
论文解读
LP-CFM: Perceptual Invariance-Aware Conditional Flow Matching for Speech Modeling
语音合成 | 7.0/10
论文解读
Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASR
语音识别 | 7.0/10
论文解读
Mixtures of Lightweight Articulatory Experts for Multilingual Asr
语音识别 | 7.0/10