AI Voice Based Attendance System

Manual attendance taking in classrooms is time-consuming, interrupts teaching and is open to proxy attendance and recording errors. This paper presents an AI Voice Based Attendance System built around an ESP32 development board. An INMP441 I2S MEMS microphone captures the speaker’s voice, and two push switches select the operating mode: switch 1 for student enrollment and switch 2 for attendance. During enrollment, voice samples of the student are recorded and converted by a SpeechBrain pre-trained speaker recognition model into a voice embedding that is stored against the student ID. During attendance, a fresh voice sample is compared with the stored embeddings and, if the similarity score crosses a threshold, the student is marked present with a time stamp. A green LED indicates successful recognition and a red LED indicates rejection, each driven through a current limiting resistor. Two role-based web dashboards are provided: an admin dashboard that shows the full student attendance data (Excel/CSV) with total present and absent counts, and a view-only HOD dashboard that shows only the total present and absent students. The system is low-cost, contactless and difficult to misuse by proxy, and it reduces the manual effort of attendance.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-18
DOI
https://doi.org/10.5281/zenodo.24331180
Primary Topic
Speech Recognition and Synthesis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AI Voice Based Attendance System

Priyanka Pawar, Prof. J. M. Patil, Nayan Lande, Akash Malage et al.
4 links
Zenodo (CERN European Organization for Nuclear Research)
Speech Recognition and Synthesis
article

AI Voice Based Attendance System

Priyanka Pawar, Prof. J. M. Patil, Nayan Lande, Akash Malage, H. T. Shaikh
article en

Abstract

Manual attendance taking in classrooms is time-consuming, interrupts teaching and is open to proxy attendance and recording errors. This paper presents an AI Voice Based Attendance System built around an ESP32 development board. An INMP441 I2S MEMS microphone captures the speaker’s voice, and two push switches select the operating mode: switch 1 for student enrollment and switch 2 for attendance. During enrollment, voice samples of the student are recorded and converted by a SpeechBrain pre-trained speaker recognition model into a voice embedding that is stored against the student ID. During attendance, a fresh voice sample is compared with the stored embeddings and, if the similarity score crosses a threshold, the student is marked present with a time stamp. A green LED indicates successful recognition and a red LED indicates rejection, each driven through a current limiting resistor. Two role-based web dashboards are provided: an admin dashboard that shows the full student attendance data (Excel/CSV) with total present and absent counts, and a view-only HOD dashboard that shows only the total present and absent students. The system is low-cost, contactless and difficult to misuse by proxy, and it reduces the manual effort of attendance.

Zenodo (CERN European Organization for Nuclear Research)
Quality education
Speech Recognition and Synthesis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon