Applying Image Recognition to Automatic Speech Recognition: Determining Suitability of Spectrograms for Training a Deep Neural Network for SpeechRecognition
Abstract
In speech recognition, Neural Networks are used to recognise the sequence of phonemes in an audio signal. These networks are trained on audio data pre-processed into some (type of) spectral vector. We present an alternative method that pre-processes speech utterances into visual representations, called spectrograms, and train a neural network suitable for image recognition to identify phonemes. The resulting network was able to classify 99.73% of a set of vowels containing samples of ‘iy’, ‘ah’ and ‘uw’ correctly, 91.87% of a set of vowels containing samples ‘iy’, ‘ih’ and ‘eh’, and 75.97% of the full dataset of twelve vowels. These results show that using image recognition in automatic speech recognition is worth further investigating.
Keywords
Not available
Specialisations
Similar theses
- A study on Human Emotion Recognition in Video Images using Deep Learning Jargalsaikhan Orgil · 2022
- Dysarthric Speech Recognition and Offline Handwriting Recognition using Deep Neural Networks Suhas Pillai · Rochester Institute of Technology · 2017
- Automatic speech recognition and machine translation with deep neural networks for open educational resources, parliamentary contents and broadcast media Gonzalo Vicente Garcés Díaz-Munío · Universitat Politècnica de València · 2024
- Deep learning neural network for image processing Xue-Qing Ma · Nanyang Technological University · 2020
- A deep convolutional neural network architecture for image classification Willem Lodewikus Pretorius · Stellenbosch University · 2020
- Implementation of Convolutional Neural Networks in FPGA for Image Classification Mark Espinosa · 2019
