Generalized Variable Parameter HMMs Based Acoustic-to-articulatory Inversion | |
Xie, Xurong; Liu, Xunying; Wang, Lan; Su, Rongfeng | |
2015 | |
会议名称 | INTERSPEECH 2015 |
会议地点 | Dresden, Germany |
英文摘要 | Acoustic-to-articulatory inversion is useful for a range of related research areas including language learning, speech production, speech coding, speech recognition and speech synthesis. HMM-based generative modelling methods and DNNbased approaches have become dominant approaches in recent years. In this paper, a novel acoustic-to-articulatory inversion technique based on generalized variable parameter HMMs (GVP-HMMs) is proposed. It leverages the strengths of both generative and neural network based modelling frameworks. On a Mandarin speech inversion task, a tandem GVP-HMM system using DNN bottleneck features as auxiliary inputs significantly outperformed the baseline HMM, multiple regression HMM (MR-HMM), DNN and deep mixture density network (MDN) systems by 0.20mm, 0.16mm, 0.12mm and 0.10mm respectively in terms of electromagnetic articulography (EMA) root mean square error (RMSE). |
收录类别 | EI |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.siat.ac.cn:8080/handle/172644/6717] ![]() |
专题 | 深圳先进技术研究院_集成所 |
作者单位 | 2015 |
推荐引用方式 GB/T 7714 | Xie, Xurong,Liu, Xunying,Wang, Lan,et al. Generalized Variable Parameter HMMs Based Acoustic-to-articulatory Inversion[C]. 见:INTERSPEECH 2015. Dresden, Germany. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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