带队代表小米AI参加INTERSPEECH旗下ConferencingSpeech2021比赛，获得非实时降噪赛道亚军

成果丰富

在INTERSPEECH2021会上进行系统技术报告

中稿Apsipa2021

Q. Wang et al., “Multi-Channel Speech Enhancement with 2-D Convolutional Time-Frequency Domain Features and a Pre-Trained Acoustic Model”, 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2021, pp. 564-570.

算法创新

提出时频域融合降噪方法，采用ASR引导降噪模型缓解语音消太多的失真问题，提升语音质量