Hooking up spectro-temporal filters with auditory-inspired representations for robust automatic speech recognition
نویسندگان
چکیده
Spectro-temporal filtering has been shown to result in features that can help to increase the robustness of automatic speech recognition (ASR) in the past. We replace the spectro-temporal representation used in previous work with spectrograms that incorporate knowledge about the signal processing of the human auditory system and which are derived from Power-Normalized Cepstral Coefficients (PNCCs). 2D-Gabor filters are applied to these spectrograms to extract features evaluated on a noisy digit recognition task. The filter bank is adapted to the new representation by optimizing the spectral modulation frequencies associated with each Gabor function. A comparison of optimized parameters and the spectral modulation of vowels shows a good match between optimized and expected range of frequencies. When processed with a non-linear neural net and combined with PNCCs, Gabor features decrease the error rate compared to the baseline and PNCCs by at least 19%.
منابع مشابه
Neural Responses to Speech-Specific Modulations Derived from a Spectro-Temporal Filter Bank
This paper analyzes the application of methods developed in automatic speech recognition (ASR) to better understand neural activity measured with electrocorticography (ECoG) during the presentation of speech. ECoG data is collected from temporal cortex in two subjects listening to a matrix sentence test. We investigate the relation of ECoG signals and acoustic speech that has been processed wit...
متن کاملNormalization of spectro-temporal Gabor filter bank features for improved robust automatic speech recognition systems
Physiologically motivated feature extraction methods based on 2D-Gabor filters have already been used successfully in robust automatic speech recognition (ASR) systems. Recently it was shown that a Mel Frequency Cepstral Coefficients (MFCC) baseline can be improved with physiologically motivated features extracted by a 2D-Gabor filter bank (GBFB). Besides physiologically inspired approaches to ...
متن کاملRobust Speech Recognition Based on Localized Spectro-temporal Features
In order to enhance automatic speech recognition performance in adverse conditions, localized spectro-temporal features (LSTF) are investigated, which are motivated by physiological measurements in the primary auditory cortex. In the Aurora2 experimental setup, Gabor-shaped LSTFs combined with a Tandem system yield robust performance with a feature set size of 30. If computational constraints a...
متن کاملRobust automatic speech recognition and modeling of auditory discrimination experiments with auditory spectro-temporal features
متن کامل
Spectro-temporal modulation subspace-spanning filter bank features for robust automatic speech recognition.
In an attempt to increase the robustness of automatic speech recognition (ASR) systems, a feature extraction scheme is proposed that takes spectro-temporal modulation frequencies (MF) into account. This physiologically inspired approach uses a two-dimensional filter bank based on Gabor filters, which limits the redundant information between feature components, and also results in physically int...
متن کامل