Spectral information is extracted on a mel scale, rather than equally across all frequency bands. We do this because humans hearing is more sensitive at lower frequencies than higher ones, so modeling speech recognition the same way helps performance.

Mel Filter Bank and Log

The categorization of texts into organized groups, which is usually implemented by supervised learning.
Applications: sentiment analysis, spam detection, news categorization, topic analysis, and more.

Text Classification

The pre-training and fine-tuning paradigm is a method motivated by the goal of creating adaptable, general-purpose systems for universal language understanding and generation. It involves separating the common components of neural network architectures, such as Transformers, and training them on vast amounts of unlabeled data using self-supervision. The resulting systems, known as foundation models, can be easily adapted for specific downstream applications via fine-tuning or prompting. This paradigm shift has enormously transformed natural language processing, meaning that in many cases, large-scale supervised learning for specific tasks is no longer required.

The Pre-training and Fine-tuning Paradigm

The formula to convert a physical acoustic frequency $$f$$ in Hertz (Hz) into its perceptual pitch in mels ($$m$$) is given by: $$m = 1127 \ln(1 + \frac{f}{700})$$

Mel Scale Conversion Formula

 A mel is a unit of pitch defined such that pairs of sounds which are perceptually equidistant in pitch are separated by an equal number of mels.

Carleton College

University of Michigan - Ann Arbor

Phonology / Phonetics

An on-going but a helpful book resource about NLP
https://web.stanford.edu/~jurafsky/slp3/

Speech and Language Processing (3rd ed. draft) 

How speech sounds are produced in the human vocal tract,
How speech sounds are realized acoustically,
How speech sounds can be digitalized and processed

Major Questions of Phonetics

The frequency of the vocal fold vibration.

Fundamental Frequency

$RMS \, amplitude_{i=1}^N = \sqrt{\frac{1}{N} \sum_{i=1}^N x_i^2}$

RMS Amplitude

Power of the Signal

The pitch of a sound is the mental sensation, or perceptual correlate, of fundamental frequency.

Pitch

Phonetic Resources

The perceived loudness of a sound is directly related to the amplitude of its sound wave. Waves with higher amplitudes are interpreted as louder sounds, while those with lower amplitudes are perceived as quieter. This perceptual quality is measured using a logarithmic unit of sound intensity called decibels (dB).

Learn Before

Related

Learn After