Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Wenning, Wei"'
Publikováno v:
Stochastic Processes and their Applications. 148:68-97
Refereed/Peer-reviewed In this paper, a Neumann problem for the backward stochastic partial differential equation (BSPDE) with singular terminal condition is studied, which characterizes the value function for a constrained stochastic control problem
In this paper, several works are proposed to address practical challenges for deploying RNN Transducer (RNN-T) based speech recognition system. These challenges are adapting a well-trained RNN-T model to a new domain without collecting the audio data
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0457c5ea92081bb2939529f0ad9dc05f
http://arxiv.org/abs/2105.00858
http://arxiv.org/abs/2105.00858
Publikováno v:
INTERSPEECH
Rapid unsupervised speaker adaptation in an E2E system posits us new challenges due to its end-to-end unified structure in addition to its intrinsic difficulty of data sparsity and imperfect label [1]. Previously we proposed utilizing the content rel
Autor:
Jian Wu, Guoli Ye, Edward Lin, Eva Sharma, Lei He, Rui Zhao, Tian Yao, Wenning Wei, Yifan Gong
Publikováno v:
ICASSP
With the advent of recurrent neural network transducer (RNN-T) model, the performance of keyword spotting (KWS) systems has greatly improved. However, the KWS systems, employed for wake-word detection, still rely on the availability of keyword specif
Publikováno v:
ICASSP
We propose to use the personalized speech synthesis and the neural language generator to synthesize content relevant personalized speech for rapid speaker adaptation. It has two distinct aspects: First, it relieves the general data sparsity issue in
Autor:
Yifan Gong, Zhong Meng, Jinyu Li, Vadim Mazalov, Sheng Zhao, Wenning Wei, Zhenghao Wang, Yanqing Liu, Lei He, Sarangarajan Parthasarathy, Rui Zhao
Publikováno v:
INTERSPEECH
Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic speech recognition. In this paper, we describe our recent development of R
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b77aca27d54edfd8e220e92fae0923c
Autor:
Jinniao Qiu, Wenning Wei
This paper is devoted to the study of fully nonlinear stochastic Hamilton-Jacobi (HJ) equations for the optimal stochastic control problem of ordinary differential equations with random coefficients. Under the standard Lipschitz continuity assumption
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::730aba804f5f4742a5f6c1880ad733e4
http://arxiv.org/abs/1807.04882
http://arxiv.org/abs/1807.04882
Autor:
Wenning Wei
Publikováno v:
Science China Mathematics. 58:1265-1284
This paper is concerned with optimal control of neutral stochastic functional differential equations (NSFDEs). The Pontryagin maximum principle is proved for optimal control, where the adjoint equation is a linear neutral backward stochastic function
Autor:
Wenning Wei
Publikováno v:
Discrete & Continuous Dynamical Systems - A. 35:5353-5378
This paper is concerned with solution in weighted Holder spaces for backward stochastic partial differential equations (BSPDEs) in a half space. Considering the solution as functional with value in Banach spaces of stochastic processes, and using the
Autor:
Jinniao Qiu, Wenning Wei
Publikováno v:
Journal of Functional Analysis. 267:3598-3656
This paper is concerned with the quasi-linear reflected backward stochastic partial differential equation (RBSPDE for short). Basing on the theory of backward stochastic partial differential equation and the parabolic capacity and potential, we first