论文解读
Speaker-Invariant Representation Learning for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck
对抗训练 | 7.1/10
Posts
论文解读
Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)
语音识别 | 8.2/10
论文解读
TinyGiantALM: A Compact Audio-Language Model for Intent-Aware Reasoning under Resource Constraints
多模态模型 | 6.4/10
论文解读
TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech
语音合成 | 8.2/10
论文解读
What Makes Synthetic Speech Sound Sarcastic? A Prosody-Controlled Perception Study
语音合成 | 7.5/10
论文解读
Your U-Net Dereverberation Model is Secretly an RIR Encoder
对比学习 | 8.3/10
每日研究速递
语音/音乐/音频论文速递 2026-06-09
共分析 48 篇语音/AI 论文
论文解读
A Large-Scale Per-Speaker Analysis of Re-identification Risk in Speech Anonymization
语音匿名化 | 7.1/10
论文解读
Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition
语音情感识别 | 7.8/10
论文解读
Assessing True Generalisability of Audio-Visual Speech Recognisers
语音识别 | 9.5/10
论文解读
Audio Imitator: Controlling Timbre and Tempo in Video2Audio Synthesis with Audio Reference
音频生成 | 6/10
论文解读
Audio-Oscar: A Multi-Agent System for Complex Audio Scene Generation, Orchestration, and Refinement
音频生成 | 9.9/10
论文解读
Beyond Semantic Dominance: Cognitive Affective Reasoning and Empathetic Response Alignment in Audio Language Models
语音合成 | 9.2/10
论文解读
BiEAR: A Human Auditory-Inspired Adaptive Binaural Front-end for Multi-Speaker Localisation and Distance Estimation
声源定位 | 8.5/10
论文解读
Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition
语音识别 | 7.1/10
论文解读
DirectAudioEdit: Inversion-Free Text-Guided Audio Editing via Diffusion Prediction Contrast
扩散模型 | 7.5/10
论文解读
dots.tts Technical Report
语音合成 | 9/10
论文解读
Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
音乐生成 | 4.2/10
论文解读
FIGMA: Towards FIne-Grained Music retrievAl
对比学习 | 7.2/10
论文解读
FSC-Net: Integrating Fast Fourier Convolutions and Progressive Learning for Speech Bandwidth Extension
音频质量评估 | 6.4/10