0 references
Adaptive boosting for automatic speech recognition
2015
Abstract
The atomic units of most automatic speech recognition (ASR) systems are the phonemes. However, the most widely used features in ASR are perceptual linear prediction (PLP) and mel-frequency cepstral coefficients (MFCC), which do not carry the phoneme information explicitly. The discriminative features with phoneme information have been shown more powerful for ASR accuracy. The process of generating the discriminative features relies on training classifiers to transform the original features to a new probabilistic features.
Related Papers
- → Deep Scattering Spectra with Deep Neural Networks for Acoustic Scene Classification Tasks(2019)22 cited
- → Sound anomaly detection of industrial products based on MFCC fusion short-time energy feature extraction(2022)3 cited
- → Feature extraction using fusion MFCC for continuous marathi speech recognition(2011)31 cited
- → Discriminative modeling by Boosting on Multilevel Aggregates(2008)13 cited
- → Research on Aesthetic Features in Computer Music Based on Spectrum Recognition and Matching Algorithm(2022)