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
语音大模型
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
论文解读
Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions
语音质量评估 | 7.1/10
论文解读
Whisper-Aware LLM: Self-Supervised Uncertainty Learning for Robust Whispered Speech Recognition
语音识别 | 6.1/10
论文解读
Speaker Role and Language Diarization for Analyzing Multilingual Interviews for Language Proficiency of Older Adults
说话人日志 | 6.3/10
论文解读
SraVaani 1.0: Scaling Inclusive Speech Recognition for Indic Languages
语音识别 | 7.9/10
论文解读
VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference
音频理解 | 7.7/10