DNN-based uncertainty estimation for weighted DNN-HMM ASR

05/29/2017
by   José Novoa, et al.
0

In this paper, the uncertainty is defined as the mean square error between a given enhanced noisy observation vector and the corresponding clean one. Then, a DNN is trained by using enhanced noisy observation vectors as input and the uncertainty as output with a training database. In testing, the DNN receives an enhanced noisy observation vector and delivers the estimated uncertainty. This uncertainty in employed in combination with a weighted DNN-HMM based speech recognition system and compared with an existing estimation of the noise cancelling uncertainty variance based on an additive noise model. Experiments were carried out with Aurora-4 task. Results with clean, multi-noise and multi-condition training are presented.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/09/2014

Spatial Diffuseness Features for DNN-Based Speech Recognition in Noisy and Reverberant Environments

We propose a spatial diffuseness feature for deep neural network (DNN)-b...
research
11/19/2019

Distributed Microphone Speech Enhancement based on Deep Learning

Speech-related applications deliver inferior performance in complex nois...
research
03/23/2018

An improved DNN-based spectral feature mapping that removes noise and reverberation for robust automatic speech recognition

Reverberation and additive noise have detrimental effects on the perform...
research
07/11/2022

pMCT: Patched Multi-Condition Training for Robust Speech Recognition

We propose a novel Patched Multi-Condition Training (pMCT) method for ro...
research
08/04/2016

An improved uncertainty decoding scheme with weighted samples for DNN-HMM hybrid systems

In this paper, we advance a recently-proposed uncertainty decoding schem...
research
10/10/2019

DOA Estimation by DNN-based Denoising and Dereverberation from Sound Intensity Vector

We propose a direction of arrival (DOA) estimation method that combines ...
research
05/04/2021

Streaming end-to-end speech recognition with jointly trained neural feature enhancement

In this paper, we present a streaming end-to-end speech recognition mode...

Please sign up or login with your details

Forgot password? Click here to reset