Brain Behind Amazon Alexa and Google Home - Automated Speech Recognition System
#datascience #machinelearning #ml
State of the art speech to text system today uses a neural network to convert speech spectrogram into a text transcript. Automated Speech Recognition system take audio data in and transcribe it to machine and human readable text
Audio data is sent through an acoustic model and a language model. Acoustic model determines the relationship between audio signals and phonetic units in a language, while a language model matches sounds to words