Speech Recognition

What’s hard about that?
•Digitization
–Converting analogue signal into digital representation
•Signal processing
– Separating speech from background noise
•Phonetics
–Variability in human speech
•Phonology
–Recognizing individual sound distinctions (similar phonemes)
•Lexicology and syntax
–Disambiguating homophones
–Features of continuous speech
•Syntax and pragmatics
–Interpreting prosodic features
•Pragmatics
–Filtering of performance errors (disfluencies)
Analogue to digital conversion
•Sampling and quantizing
•Use filters to measure energy levels for various points on the frequency spectrum
•Knowing the relative importance of different frequency bands (for speech) makes this process more efficient
•E.g. high frequency sounds are less informative, so can be sampled using a broader bandwidth (log scale)
The frequency range of sounds perceived by humans is something between 30 Hz (hertz, cycles per second) and 20,000 Hz. Above 20K we hear nothing.
•The acoustic file need to format in which speech data can be saved. In recent years the most popular format (most frequently used format) has been Microsoft WAV format. There are many other formats( MKV, AVI.MP3). The difference is in how many samples occur per second, and exactly each sample is represented