Page Not Found
Page not found. Your pixels are in another canvas.
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Page not found. Your pixels are in another canvas.
About me
Research, Institute of Acoustics, Chinese Academy of Sciences, 2017
研究最优波束形成理论,提高波束形成器在强背景噪音和强干扰环境下的性能
Project, Georgia Tech, Center for Signal and Image Processing, 2018
与三星总部研究院合作研发家居环境的远场语音识别系统
Research, Georgia Tech, Center for Signal and Image Processing, 2019
研究基于DNN的存在干扰人情况下的远讲语音分离、增强、去混响方法
Project, Xiaomi, AI lab, 2021
超越原音箱声学模型5%~10% 英文ASR超越微软接口
Project, Xiaomi, AI lab, 2021
构建可落地的个性化ASR:大幅改善障碍人士、线上重口音用户的语音识别率
Challenge/Research, Xiaomi, AI lab, 2021
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
Project/Research, Xiaomi, AI lab, 2021
从0到1构建多通道ASR范式:构建大规模数据集、算法和评测集,对标谷歌、百度
Challenge/Research, Xiaomi, AI lab, 2022
带队代表小米AI参加ICASSP旗下MISP2021挑战赛,赢得音视频唤醒赛道冠军,音视频识别赛道亚军
Research, Xiaomi, AI lab, 2022
和小米首席语音科学家Daniel Povey合作,重新定义知识蒸馏问题为一个编解码问题,将大规模预训练模型的能力迁移到下游ASR模型。相比于传统蒸馏方式快至少4.5倍(或者存储空间节省640倍),性能相对提升11.12%。