Improved DNN-HMM English Acoustic Model Specially For Phonotactic Language Recognition
Asian Language Processing (IALP), 2019 International Conference on,
2019 Nov,
2019년, pp.343 - 348
Liu, Wei-Wei
(Tsinghua University,Department of Electronic Engineering,Beijing,China,100842)
,
Yin, Ying
(Tsinghua University,Department of Electronic Engineering,Beijing,China,100842)
,
Li, Ya-Nan
(Academy of Military Science,Beijing,China,100091)
,
Huang, Yu-Bin
(Tsinghua University,Department of Electronic Engineering,Beijing,China,100842)
,
Ruan, Ting
(Tsinghua University,Department of Electronic Engineering,Beijing,China,100842)
,
Liu, Wei
(Tsinghua University,Department of Electronic Engineering,Beijing,China,100842)
,
Du, Rui-Li
(Tsinghua University,Department of Electronic Engineering,Beijing,China,100842)
,
Bai, Hua-ying
(Tsinghua University,Department of Electronic Engineering,Beijing,China,100842)
,
Li, Wei
(Tsinghua University,Department of Electronic Engineering,Beijing,China,100842)
,
Zhang, Sheng-Ge
(Tsinghua University,Department of Electronic Engineering,Beijing,China,100842)
,
Li, Guo-Chun
(Tsinghua University,Department of Electronic Engineering,Beijing,China,100842)
,
Zhang, Cun-Xue
(Tsinghua University,Department of Electronic Engineering,Beijing,China,100842)
,
Yan, Hai-Feng
(Tsinghua University,Department of Electronic Engineering,Beijing,Chin)
,
He, Jing
,
Gan, Ying-Xin
,
Song, Yan-Miao
,
Zhou, Jian-Hua
,
Liu, Jian-Zhong
The now-acknowledged sensitive of Phonotactic Language Recognition (PLR) to the performance of the phone recognizer front-end have spawned interests to develop many methods to improve it. In this paper, improved Deep Neural Networks Hidden Markov Model (DNN-HMM) English acoustic model front-end spec...
The now-acknowledged sensitive of Phonotactic Language Recognition (PLR) to the performance of the phone recognizer front-end have spawned interests to develop many methods to improve it. In this paper, improved Deep Neural Networks Hidden Markov Model (DNN-HMM) English acoustic model front-end specially for phonotactic language recognition is proposed, and series of methods like dictionary merging, phoneme splitting, phoneme clustering, state clustering and DNN-HMM acoustic modeling (DPPSD) are introduced to balance the generalization and the accusation of the speech tokenizing processing in PLR. Experiments are carried out on the database of National Institute of Standards and Technology language recognition evaluation 2009 (NIST LRE 2009). It is showed that the DPPSD English acoustic model based phonotactic language recognition system yields 2.09%, 6.60%, 19.72% for 30s, 10s, 3s in equal error rate (EER) by applying the state-of-the-art techniques, which outperforms the language recognition results on both TIMIT and CMU dictionary and other phoneme clustering methods.
The now-acknowledged sensitive of Phonotactic Language Recognition (PLR) to the performance of the phone recognizer front-end have spawned interests to develop many methods to improve it. In this paper, improved Deep Neural Networks Hidden Markov Model (DNN-HMM) English acoustic model front-end specially for phonotactic language recognition is proposed, and series of methods like dictionary merging, phoneme splitting, phoneme clustering, state clustering and DNN-HMM acoustic modeling (DPPSD) are introduced to balance the generalization and the accusation of the speech tokenizing processing in PLR. Experiments are carried out on the database of National Institute of Standards and Technology language recognition evaluation 2009 (NIST LRE 2009). It is showed that the DPPSD English acoustic model based phonotactic language recognition system yields 2.09%, 6.60%, 19.72% for 30s, 10s, 3s in equal error rate (EER) by applying the state-of-the-art techniques, which outperforms the language recognition results on both TIMIT and CMU dictionary and other phoneme clustering methods.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.