Modified SPLICE and its Extension to Non-Stereo Data for Noise Robust Speech Recognition

07/15/2013
by   D. S. Pavan Kumar, et al.
0

In this paper, a modification to the training process of the popular SPLICE algorithm has been proposed for noise robust speech recognition. The modification is based on feature correlations, and enables this stereo-based algorithm to improve the performance in all noise conditions, especially in unseen cases. Further, the modified framework is extended to work for non-stereo datasets where clean and noisy training utterances, but not stereo counterparts, are required. Finally, an MLLR-based computationally efficient run-time noise adaptation method in SPLICE framework has been proposed. The modified SPLICE shows 8.6 Aurora-2 database, and 2.93 absolute improvements over Aurora-2 and Aurora-4 baseline models respectively. Run-time adaptation shows 9.89 compared to SPLICE for Test C, and 4.96 adaptation on HMMs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/14/2015

Feature Normalisation for Robust Speech Recognition

Speech recognition system performance degrades in noisy environments. If...
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
03/09/2015

Modeling State-Conditional Observation Distribution using Weighted Stereo Samples for Factorial Speech Processing Models

This paper investigates the effectiveness of factorial speech processing...
research
07/15/2022

Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments

This paper describes noisy speech recognition for an augmented reality h...
research
02/28/2023

deHuBERT: Disentangling Noise in a Self-supervised Model for Robust Speech Recognition

Existing self-supervised pre-trained speech models have offered an effec...
research
02/15/2020

Small energy masking for improved neural network training for end-to-end speech recognition

In this paper, we present a Small Energy Masking (SEM) algorithm, which ...

Please sign up or login with your details

Forgot password? Click here to reset