论文解读
Benchmarking Neural Speech Compression from a Rate-Distortion Perspective
基准测试 | 9/10
论文速递
论文解读
Context-Aware Multimodal Claim Verification in Spoken Dialogues
多模态模型 | 7.1/10
论文解读
CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech
多语言 | 9.2/10
论文解读
Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models
语音识别 | 8.8/10
论文解读
Fast Speech Foundation Model Distillation Using Interleaved Stacking
知识蒸馏 | 6.6/10
论文解读
Fast-SDE: Efficient Single-Microphone Sound Source Distance Estimation in Reverberant Environments
Fast-SDE: Efficient Single-Microphone Sound Source Distance Estimation in Reverberant Environments
论文解读
Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions
鲁棒性 | 7.1/10
论文解读
Frozen Multimodal Embeddings for Personality and Cognitive Ability Assessment in Asynchronous Video Interviews
语音情感识别 | 6.7/10
论文解读
Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains
语音识别 | 9.1/10
论文解读
HALO: Half-Frame-Rate Adaptive Learnable Operator for Lightweight STFT-Based Speech Enhancement
语音增强 | 8.4/10
论文解读
I Understand How You Feel: Enhancing Deeper Emotional Support Through Multilingual Emotional Validation in Dialogue System
语音识别 | 5.8/10
论文解读
Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders
语音合成 | 7.7/10
论文解读
Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization
语音合成 | 6.8/10
论文解读
Lung-SRAD: Spectral-Aware Regularized Audio DASS with Dual-Axis Patch-Mix Contrastive Learning for Respiratory Sound Classification
对比学习 | 6.8/10
论文解读
MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation
语音情感识别 | 7.5/10
论文解读
Massive Open-Vocabulary Keyword Spotting
语音识别 | 9.8/10
论文解读
Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering
基准测试 | 5.5/10
论文解读
PianoKontext: Expressive Performance Rendering from Deadpan Context
音乐生成 | 9.1/10
论文解读
Pretrained self-supervised speech models can recognize unseen consonants
语音识别 | 6.5/10
论文解读
Quality Adaptive Angular Margin Learning for Respiratory Sound Classification
音频质量评估 | 9.5/10