Recognizing reverberant speech with RASTA-PLP
نویسندگان
چکیده
The performance of the PLP, log-RASTA-PLP, and J-RASTA-PLP front ends for recognition of highly reverberant speech is measured and compared with the performance of humans and the performance of an experimental RASTA-like front end on reverberant speech, and with the performance of a PLP-based recognizer trained on reverberant speech. While humans are able to reliably recognize the reverberant test set, achieving a 6.1% word error rate, the best RASTA-PLP-based recognizer has a word error rate of 68.7% on the same test set, and the PLP-based recognizer trained on reverberant speech has a 50.3% word error rate. Our experimental variant on RASTA processing provides a statistically signi cant improvement in performance on the reverberant speech, with a best word error rate of 64.1%.
منابع مشابه
Deployment of Rasta-plp with the Siemens Zt Speech Recognition System
RelAtive SpecTral Analysis-Perceptual Linear Prediction (RASTA-PLP) is the standard speech feature extraction method used at the International Computer Science Institute. There it has been used primarily in conjunction with a hybrid Artiicial Neural Network (ANN) and Hidden Markov Model (HMM) speech recognition system. This work explores the viability of the RASTA-PLP as a candidate feature ext...
متن کاملRobust speech recognition using the modulation spectrogram
The performance of present-day automatic speech recognition (ASR) systems is seriously compromised by levels of acoustic interference (such as additive noise and room reverberation) representative of real-world speaking conditions. Studies on the perception of speech by human listeners suggest that recognizer robustness might be improved by focusing on temporal structure in the speech signal th...
متن کاملData-driven RASTA filters in reverberation
In this work we test the performance of RASTA-style modulation filters derived under reverberant conditions. The modulation filters are constructed through linear discriminant analysis of log critical band energies in a manner described by van Vuuren and Hermansky. In previous work we had observed the properties of the resultant filters under a number of acoustic conditions that were artificial...
متن کاملMulti-resolution RASTA filtering fo
New speech representation based on multiple filtering of temporal trajectories of speech energies in frequency sub-bands is proposed and tested. The technique extends earlier works on delta features and RASTA filtering by processing temporal trajectories by a bank of band-pass filters with varying resolutions. In initial tests on OGI Digits database the technique yields about 30% relative impro...
متن کاملMRASTA and PLP in automatic speech recognition
This work explores different methods for combining estimated posterior probabilities from Multi-RASTA (MRASTA) and Perceptual Linear Prediction (PLP) features for Automatic Speech Recognition (ASR). The improved performance by the ASR system indicates the complementary nature of information present in MRASTA and PLP. Among the different combining methods explored, product gives best performance.
متن کامل