RNN-LDA Clustering for Feature Based DNN Adaptation
文献类型：会议论文
| 作者 | Xie, Xurong; Liu, Xunying; Lee, Tan; Wang, Lan |
| 出版日期 | 2017 |
| 会议地点 | 瑞典 斯德哥尔摩 |
| 英文摘要 | Model based deep neural network (DNN) adaptation approaches often require multi-pass decoding in test time. Input feature based DNN adaptation, for example, based on latent Dirichlet allocation (LDA) clustering, provide a more efficient alternative. In conventional LDA clustering, the transition and correlation between neighboring clusters is ignored. In order to address this issue, a recurrent neural network (RNN) based clustering scheme is proposed to learn both the standard LDA cluster labels and their natural correlation over time in this paper. In addition to directly using the resulting RNN-LDA as input features during DNN adaptation, a range of techniques were investigated to condition the DNN hidden layer parameters or activation outputs on the RNN-LDA features. On a DARPA Gale Mandarin Chinese broadcast speech transcription task, the proposed RNN-LDA cluster features adapted DNN system outperformed both the baseline un-adapted DNN system and conventional LDA features adapted DNN system by 8% relative on the most difficult Phoenix TV subset. Consistent improvements were also obtained after further combination with model based adaptation approaches. |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/11776]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2017 |
| 推荐引用方式 GB/T 7714 | Xie, Xurong,Liu, Xunying,Lee, Tan,et al. RNN-LDA Clustering for Feature Based DNN Adaptation[C]. 见:. 瑞典 斯德哥尔摩. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
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。