面向智能设备的听觉感知关键技术研究(research on audio perception for intelligent devices)
研究方向
- 基于小型或微型传感器阵列的空间声源感知算法研究与系统实现(DOA estimation based on small microphone array);
- 语音增强与噪声消除方法(speech enhancement and noise reduction);
- 自然环境移动互联设备的语音接口技术:语音识别,声纹识别,情感识别等(audio IO: speech recognition, voice print, and Sentiment analysis)
- 自然环境中的音频监控技术(audio event monitoring)。
模式识别、机器学习及其应用(pattern recognition, machine learning, and applications)
- 模式识别理论及应用(pattern recognition principles and applications);
- 基于深度学习的模式识别理论及应用(pattern recognition based on DNN and applications);
- 基于稀疏表示和字典学习的模式识别理论及应用(Pattern recognition with sparse representation and dictionary learning)
- 面向智能监控的视频摘要和目标分类方法(video summarization and object classification for video surveillance);
- 基于学习的医学图像增强与分类方法(image enhancement and image classification based on learning);