Saliency is the prominence of a certain syllable through changes in volume, duration, or frequency. Prominent words and syllables bear pitch accents, and accented syllables hold lexical stress.

Saliency

Sentences have prosodic phrasing, where some parts of an utterance seem to group naturally together in intonation phrases, which are in turn made of intermediate phrases.

Prosodic Phrasing

Tune is the rise and fall of F0 in a sentence.


Tune

Prosody is the study of rhythm and intonation in language through F0 (fundamental frequency), energy, and duration of utterances. 

San Jose State University

University of California, Santa Cruz

Google

Phonetics is the field of study in which speech sounds from world languages are studied - how they are created in a vocal tract, how they materialize in an acoustic sense, and how they can be relayed or processed digitally. 

Phonetics

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

Speech and Language Processing (3rd ed. draft) 

A phone is a speech sound which is typified by adapted symbols from the Roman alphabet. Any word's pronunciation can be represented as a string of phones.

Phones (phonetics)

The International Phonetic Alphabet (IPA) is the ever-developing standard phonetic representation for transcribing the world's languages. It was first developed in 1888.

Learn Before

Related

Learn After