Paper Key : IRJ************429
Author: Aiswarya P A , Ms. Arya K A
Date Published: 17 Nov 2023
Abstract
AbstractSpeech along with other utterances that carry meaning are referred to as spoken language. Most people communicate in at least one native language that they learned as children and additional languages that they have learned throughout the course of their lifetime. Different languages have different rules for how consonant and vowel sounds can be combined into syllables in words. The vocal and auditory abilities of humans allow for a very wide variety of articulations and subsequent sounds, all of which are used in spoken language. Each spoken language has a slightly varied range, which contributes to the challenge of learning a foreign language and expressing it with an accent. Spoken language identification (SLID) is the method of identifying language from an audio clip by an unknown speaker, regardless of gender, speaking style, or age. In this study, numerous spoken language identification models have been developed by utilizing various deep learning techniques, machine learning techniques, datasets, and performance metrics. Data gathering, feature elimination, and language classification are the three core components of the SLID system.
DOI LINK : 10.56726/IRJMETS45611 https://www.doi.org/10.56726/IRJMETS45611