Knowledge Commons of Institute of Automation,CAS
Complex Dynamic Neurons Improved Spiking Transformer Network for Efficient Automatic Speech Recognition | |
Qingyu Wang1,2; Tielin Zhang1,2; Minglun Han1,2; Yi Wang4; Duzhen Zhang1,2; Bo Xu1,2,3 | |
2023-05 | |
会议名称 | Thirty-Seventh AAAI Conference on Artificial Intelligence |
会议日期 | 2023-2-9 |
会议地点 | Washington D.C., USA |
摘要 | The spiking neural network (SNN) using leaky-integrated-and-fire (LIF) neurons has been commonly used in automatic speech recognition (ASR) tasks. However, the LIF neuron is still relatively simple compared to that in the biological brain. Further research on more types of neurons with different scales of neuronal dynamics is necessary. Here we introduce four types of neuronal dynamics to post-process the sequential patterns generated from the spiking transformer to get the complex dynamic neuron improved spiking transformer neural network (DyTr-SNN). We found that the DyTr-SNN could handle the non-toy automatic speech recognition task well, representing a lower phoneme error rate, lower computational cost, and higher robustness. These results indicate that the further cooperation of SNNs and neural dynamics at the neuron and network scales might have much in store for the future, especially on the ASR tasks. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 类脑模型与计算 |
国重实验室规划方向分类 | 语音语言处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52078 |
专题 | 复杂系统认知与决策实验室_听觉模型与认知计算 |
通讯作者 | Tielin Zhang; Bo Xu |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 3.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, China 4.School of Artificial Intelligence, Jilin University, Changchun, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Qingyu Wang,Tielin Zhang,Minglun Han,et al. Complex Dynamic Neurons Improved Spiking Transformer Network for Efficient Automatic Speech Recognition[C],2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
AAAI-2023.pdf(1714KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论