Speech recognition is an important field in deep learning with multiple applications. Speech is a fundamental
form of human communication. Speech recognition involves converting spoken language into written text
or data that could be understood by machines. Speech data refers to audio recordings of human speech,
while phonemes represent the smallest units of sound that can convey a different meaning(bake, take: b,t).
Spectrograms are visual representations of the acoustic properties of speech signals, i.e. captures the changes
in the frequency over time.