Abstract: This paper presents the speaker recognition and language recognition system. Speaker recognition is done using three coders and the performance or accuraccy for each coder is calculated. Speaker recognition is the process to identify a person using characteristics extracted from their voices. While language recognition is the process to identify the language of speaker. In this paper, speaker recognition is done using three different coders at different bit rate. Here GSM at 12.2 kb/s, G.729 at 8 kb/s, and G.723.1 at 5.3 kb/s speech coders are used[3]. The task of language recognition is done using phonetic approach[10].

Keywords: GSM at 12.2 kb/s, G.729 at 8 kb/s, and G.723.1 at 5.3 kb/s, phonetic approach.