Locally Normalized Filter Banks Applied to Deep Neural-Network-Based Robust Speech Recognition
Authors:
- 31 January 2017
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 24 (4) , 377-381
Abstract
This letter describes modifications to locally normalized filter banks (LNFB), which substantially improve their performance on the Aurora-4 robust speech recognition task using a Deep Neural Network-Hidden Markov Model (DNN-HMM)-based speech recognition system. The modified coefficients, referred to as LNFB features, are a filter-bank version of locally normalized cepstral coefficients (LNCC), which have been described previously. The ability of the LNFB features is enhanced through the use of newly proposed dynamic versions of them, which are developed using an approach that differs somewhat from the traditional development of delta and delta-delta features. Further enhancements are obtained through the use of mean normalization and mean-variance normalization, which is evaluated both on a per-speaker and a per-utterance basis. The best performing feature combination (typically LNFB combined with LNFB delta and delta-delta features and mean-variance normalization) provides an average relative reduction in word error rate of 11.4% and 9.4%, respectively, compared to comparable features derived from Mel filter banks when clean and multinoise training are used for the Aurora-4 evaluation. The results presented here suggest that the proposed technique is more robust to channel mismatches between training and testing data than MFCC-derived features and is more effective in dealing with channel diversity.Keywords
Funding Information
- CONICYT-Fondecyt (1151306)
- CONICYT-Anillo (ACT 1120)
This publication has 18 references indexed in Scilit:
- A perceptually-motivated low-complexity instantaneous linear channel normalization technique applied to speaker verificationComputer Speech & Language, 2015
- Robust excitation-based features for Automatic Speech Recognition2015
- Deep Neural Networks2014
- A Spectral Masking Approach to Noise-Robust Speech Recognition Using Deep Neural NetworksIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- An investigation of deep neural networks for noise robust speech recognition2013
- Efficient BackProp2012
- Feature Extraction for ASR2011
- Cepstral domain segmental feature vector normalization for noise robust speech recognitionSpeech Communication, 1998
- Speaker-independent isolated word recognition using dynamic features of speech spectrumIEEE Transactions on Acoustics, Speech, and Signal Processing, 1986
- Analytical expressions for critical-band rate and critical bandwidth as a function of frequencyThe Journal of the Acoustical Society of America, 1980