Year: 2024
Type: article
Abstract: Audio segmentation represents a technical process used for separating a stream of audio recordings, which frequently contain multiple speakers, into uniform sections. This paper explores the implementation of voice-dialing and recognition algorithms to examine and analyze the technology's capability to accurately identify and differentiate speakers in intricate environments. It aims to enhance our understanding of the technology's functionality, including its ability to discern speakers' emotions and gender. Additionally, a hardware simulation is conducted using a two-way microphone and an Arduino board. It seeks to emphasize precision in speaker recognition and diarization, along with the accurate transcription of speeches, by achieving optimal parameters and enhancing existing market models. It also explores the applicability of this technology in various fields by creating applications that mainly use Speech Diarization and Speech Recognition.
Authors: Fatemeh DARGAHI, Costin-Alexandru DEONISE, Constantin ANGHEL, Cătălin Negru, Florin Pop
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4406773034