学号 | BA20006026 | ||
姓名 | 陈航 | ||
所在院系 | 006电子工程与信息科学系 | ||
申请专业 | 信息与通信工程 | ||
学位论文自我评价 | 论文题目 | 面向音视频语音增强与识别的建模方法研究 | |
主要创新点 |
|||
1. | |||
2. | |||
3. | |||
有待改进之处 |
|||
答辩结果 | 通过:5 建议修改: 不通过:0 | ||
发表论文情况: | |||
发表论文(1) | Correlating subword articulation with lip shapes for embedding aware audio-visual speech enhancement | ||
论文(1)发表期刊 | NEURAL NETWORKS(SCI一区, 9.657) | 位于科大期刊目录第0页第0条 | |
论文(1)发表刊次 | 143 (2021) 171-182 | 论文(1)作者排名:本人第一 | |
发表论文(2) | Correlated multi-level speech enhancement for robust real-world asr applications using mask-waveform-feature optimization | ||
论文(2)发表期刊 | Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) | 位于科大期刊目录第0页第0条 | |
论文(2)发表刊次 | 31 October - 3 November 2023, EI: 20235115257095 | 论文(2)作者排名:本人第一 | |
发表论文(3) | The first multimodal information based speech processing (MISP) challenge: data, tasks, baselines and results | ||
论文(3)发表期刊 | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | 位于科大期刊目录第0页第0条 | |
论文(3)发表刊次 | 23 - 27 May 2022, EI: 20222312198975 | 论文(3)作者排名:本人第一 | |
发表论文(4) | Audio-visual speech recognition in misp2021 challenge: dataset release and deep analysis | ||
论文(4)发表期刊 | Annual Conference of the International Speech Communication Association (INTERSPEECH) | 位于科大期刊目录第0页第0条 | |
论文(4)发表刊次 | 18 - 22 September 2022, EI: 20224312992997 | 论文(4)作者排名:本人第一 | |
发表论文(5) | Automatic lip-reading with hierarchical pyramidal convolution and self-attention for image sequences with no word boundaries | ||
论文(5)发表期刊 | Annual Conference of the International Speech Communication Association (INTERSPEECH) | 位于科大期刊目录第0页第0条 | |
论文(5)发表刊次 | 30 August - 3 September 2021, EI: 20214711186832 | 论文(5)作者排名:本人第一 | |
发表论文(6) | Summary on the Multimodal Information Based Speech Processing (MISP) 2022 Challenge | ||
论文(6)发表期刊 | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | 位于科大期刊目录第0页第0条 | |
论文(6)发表刊次 | 4 - 10 June 2023, EI:20240815586015 | 论文(6)作者排名:本人第一 |