NepaliONE: Building an Onomatopoeic Speech Corpus for Enhancing Expression and Emotion in Nepali Text-to- Speech Synthesis

Nepali, like many major Indian languages of the Indo-Aryan and Dravidian families,
is rich in expressive linguistic forms such as ideophones, onomatopoeic expressions, echo words,
exclamations, and reduplicative constructions. Among these, Nepali onomatopoeia exhibits strong
phonaesthetic qualities that convey precise meanings and evoke vivid sensory imagery. However,
this distinctive lexical category has gradually declined in everyday usage among Nepali speakers.
This paper presents NepaliONE, a sentence-aligned expressive speech corpus focusing on Nepali
onomatopoeic vocabulary.