Corrected tandem features for acoustic model training

Abstract

This paper describes a simple method for significantly improving Tandem features used to train acoustic models for large-vocabulary speech recognition. The linear activations at the outputs of an MLP classifier were modified according to known reference labels: where necessary, the activation of the output unit corresponding to the correct phone label was increased in order to make an accurate classification. This technique was inspired by another experiment that determined a lower error bound on ASR performance within the Tandem framework. By simulating an idealized classifier with forward-backward phone posterior probabilities, we observed a best-case scenario in which nearly all errors were eliminated. Although this performance is not practically achievable, the experiment demonstrated the validity of the Tandem processing approach and suggested that considerable gains are possible by improving the MLP phone classifier.

A Novel Fiber Optic Based Surveillance System for Prevention of Pipeline Integrity Threats

“…The contextual feature extraction is based on the tandem approach used to compute the so-called tandem features in speech recognition tasks [ 45 , 46 , 47 ]. This module takes the normalized frequency-based feature vectors as input and produces tandem feature vectors as output.…”

Deep Learning Based Threat Classification for Fiber Optic Distributed Acoustic Sensing Using SNR Dependent Data Generation

“…As is known, in a typical classification problem, the features that are extracted from signals are critical to the classification performance. For this reason, in the ODTR vibration classification studies of various feature extraction methods such as energy of frequency bins [8], Speech Recognition features such as Tandem features [10], morphological feature extraction method [11] and Mel Frequency Cepstrum Coefficients (MFCC) features [12] have achieved significant performance.…”