Convolutional Neural Network Bottleneck Features for bi-directional Generalized Variable Parameter HMMs
文献类型：会议论文
| 作者 | Rongfeng Su; Xunying Liu; Lan Wang |
| 出版日期 | 2016 |
| 会议名称 | ICIA2016 |
| 会议地点 | 中国宁波 |
| 英文摘要 | Recently, convolutional neural networks (CNNs) have been applied successfully to acoustic modelling in speech recognition. As the bottleneck features from CNNs contain inherently discriminative and rich context information, the standard approach is to augment the conventional acoustic features with the CNN bottleneck features in a tandem framework. To better capture the highly complex relationship between them, a novel bidirectional generalized variable parameter HMM (GVP-HMM) based approach is proposed in this paper. In this approach, the trajectories of continuous acoustic features space HMM parameters, as well as the model space linear transforms against CNN bottleneck features are modelled by polynomial functions. The optimal GVP-HMM model structure for each direction, which is determined by the locally varying polynomial parameters and degrees, can be automatically learnt using model selection techniques. The proposed bi-directional GVP-HMM based approach gave a word error rate of 12.22% on the Aurora 4 task. In particular, a significant error rate reduction of 18.09% relative was obtained over the baseline tandem HMM system using CNN bottleneck features on the secondary microphone channel condition. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/10031]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2016 |
| 推荐引用方式 GB/T 7714 | Rongfeng Su,Xunying Liu,Lan Wang. Convolutional Neural Network Bottleneck Features for bi-directional Generalized Variable Parameter HMMs[C]. 见:ICIA2016. 中国宁波. |
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。