acoustic signal processing; feature extraction; speech recognition; support vector machines; acoustic aspects; feature extraction; hand-crafted features; human communication; multiclass SVM; sound retrieval; stacked auto-encoder; vocal imitation recognition; Accuracy; Feature extraction; Instruments; Semantics; Support vector machines; Synthesizers; Sound retrieval; automatic feature learning; multi-class classification; stacked auto-encoder; vocal imitation;
机译:减慢面部运动和人声的表现,可增强自闭症儿童的面部表情识别能力并诱导其面部-声音模仿
机译:使用模型对听觉接收领域的语气仿真模拟中的三个明晰度类别的预测
机译:通过人声模仿进行有监督和无监督的声音检索
机译:通过人声模仿识别检索声音
机译:声音模仿声音搜索
机译:纠正:敲击声音的人声模仿:关于模仿声音和模仿声音之间的感知相似性
机译:通过声乐模仿识别检索声音