论文解读
会打断、会附和，还要听得懂分寸：把“何时说话”从“说什么”里拆出来
语音交互 | 7.3/10
语音大模型
论文解读
给大模型加声学缰绳：用 0.6 nats 的似然约束把翻译式幻觉拉回转录
语音识别 | 7.8/10
论文解读
口音不是噪声，是距离：当母语离英语越远，ASR 的潜空间就越把你推开
语音识别 | 6.9/10
论文解读
当语音和文本各说各话，重排器如何当翻译官？
LoRA | 5.8/10
论文解读
当一句非洲对话里藏着两种语言，语音识别该听哪一种？
语音识别 | 8.1/10
论文解读
听错一个字就全盘皆输：SpeechGym 把语音智能体的失败变成可训练的梯度
语音交互 | 7.6/10
论文解读
克隆与匿名本是一体两面：把 27k 小时的 TTS 直接当成隐私滤镜
语音转换 | 8.0/10
论文解读
Relative Time Intervals Representation for Word-level Timestamping with Masked Training
语音识别 | 8.6/10
论文解读
Speech-to-SOAP: End-to-End Summarization of Medical Dialogues: KIT@BeTraC 2026
音频理解 | 7.7/10
论文解读
DiaScriber: A Speech LLM for Joint Diarization and Transcription in Multi-Speaker Scenarios
语音识别 | 7.3/10
论文解读
Do SpeechLMs Hear Their Own Opinions? Diagnosing and Mitigating Previous-Belief Contamination in Streaming Emotion Understanding
语音情感识别 | 8.9/10
论文解读
Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text
语音交互 | 10.0/10
论文解读
WnW: Waxing-and-Waning KV Cache for Long-Form Speech LLMs
语音交互 | 9.4/10
论文解读
Aslema at NADI 2026: Augmentation through Fewshot for SLU
语音交互 | 8.0/10
论文解读
A survey of AI-generated voices and their detection
语音伪造检测 | 6.1/10
论文解读
DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech
语音合成 | 6.1/10
论文解读
Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation
语音识别 | 5.6/10
论文解读
VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents
语音合成 | 8.2/10
论文解读
Rethinking Language Model-Based Generative Speech Enhancement in the Latent Space of a Neural Audio Codec
语音增强 | 7.1/10
论文解读
The SLT 2026 SmartGlasses Challenge: Benchmarking Egocentric Multi-Talker Speech Recognition and Understanding with Audio-Language Models
语音识别 | 7.5/10