论文解读
想练好一句难开口的话，机器得先学会怎么“演人”：Conversation Coach 的延迟与演技取舍
语音交互 | 6.3/10
端到端
论文解读
把响度与形状拆开：用归一化解耦让板混响参数在病态地形中收敛
音乐理解 | 6.3/10
论文解读
用最轻的耳蜗换最高的精度：HLP 脉冲编码为何在干净数据上赢、在嘈杂数据上输
语音识别 | 6.8/10
论文解读
韵律能猜出多少句法？把停顿与时长放进互信息的秤上称重
Transformer | 7.6/10
论文解读
不用再把 PDM 翻译成 PCM：让状态空间模型直接听懂单比特麦克风
语音增强 | 7.5/10
论文解读
把拾音器从琴上焊死的位置里解放出来：64 路沿弦采样如何把音色选择推迟到混音台
音乐源分离 | 7.7/10
论文解读
把嘴边的电极收回指尖：按需贴合如何让无声语音既可用又不打扰隐私
语音识别 | 5.9/10
论文解读
不只给一个抑郁概率：把声音拆成四条可审计的 DSM-5 线索
语音情感识别 | 7.1/10
论文解读
别让检测器猜伪迹：先把原声的压缩记忆藏回去
语音伪造检测 | 6.5/10
论文解读
One Timeline, Many Renderings: A Wolfram Language Paclet for heterogeneous musical output
音乐生成 | 7.0/10
论文解读
REDnet: Recursive Encoder and Decoder for Speech Separation under Unknown Number of Speakers and Variable Number of Microphones
语音分离 | 8.2/10
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
Humanoid Musical Robots as Experimental Interfaces for Music-Evoked Emotion
音视频交互 | 5.9/10
论文解读
Vibrato Matching for Modulation Control and Blending in Sound Mixtures
音频生成 | 8.5/10
论文解读
Accurate Decoding of Natural Sentences from Non-Invasive Brain Recordings
语音识别 | 7.5/10
论文解读
FM Synthesizer Audio-Parameter Shared Embeddings
音频生成 | 7.3/10
论文解读
Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring
音频分类 | 7.3/10
论文解读
Mitigating Spectral Bias in Neural Operators for Underwater Transmission Loss Prediction
音频理解 | 7.3/10
论文解读
StocksTalk: A Voice-Enabled Conversational Agent for Structured Query Generation over Web Data
语音交互 | 6.7/10
论文解读
Impulse Response Estimation via Laguerre-Fourier Expansion
音频理解 | 6.8/10