Description:
ATTENDANCE SYSTEM USING SPEECH RECOGNITION AND METHOD THEREOF
BACKGROUND
Technical Field
[0001] The embodiment herein generally relates to an attendance system and fermentation technology and more particularly, to an attendance system using speech recognition and method thereof.
Description of the Related Art
[0002] Generally, attendance monitoring system is manual and due to recent advancement in technology, the attendance monitoring system is made automatic. Further the automatic attendance monitoring system uses biometrics. Existing biometric feature of the automatic attendance monitoring system uses finger print scanning and retina scanning of a person to capture attendance.
[0003] Also the finger print scanning and the retina scanning are physical devices which is expensive.
[0004] Accordingly, there remains a need for an attendance system using speech recognition and method thereof.
SUMMARY
[0005] In view of the foregoing, embodiments herein provide an attendance system using speech recognition, The system includes a voice input receiving module, a voice preprocessing module, a feature extraction module, a text analysis module, a speaker verification module, an attendance logging module, and an admin interface module. The voice input receiving module is configured to record voice from speaker. The voice preprocessing module is configured to preprocess the record voice to remove noise. The feature extraction module is configured to convert raw waveform of the preprocessed recorded voice to text using deep learning models. The text analysis module is configured to extracts key identifiers from the extracted features. The speaker verification module is configured to compares extracted key identifiers with stored profiles. The attendance Logging module is configured to mark an attendance of a person if the key identifiers match with the stored profile of the person. The admin interface module is configured to record the attendance of the person.
[0006] In some embodiments, the key identifiers includes names or IDs of the person.
[0007] In some embodiments, the system further includes a Bluetooth low energy (BLE) integration module that is configured to prevents proxy attendance.
[0008] In some embodiments, the voice input is a predefined phrase which is spoken by the person.
[0009] In another aspect of the embodiments herein provides a method of proving an attendance system using speech recognition. The method includes configuring, a voice input receiving module, to record voice from speaker. The method further includes configuring, a voice preprocessing module, to preprocess the record voice to remove noise. The method further includes configuring, a feature extraction module, to convert raw waveform of the preprocessed recorded voice to text using deep learning models. The method further includes configuring, a text analysis module, to extracts key identifiers from the extracted features. The method further includes configuring, a speaker verification module, to compares extracted key identifiers with stored profiles. The method further includes configuring, an attendance logging module, to mark an attendance of a person if the key identifiers match with the stored profile of the person. The method further includes configuring, an admin interface module, to record the attendance of the person.
[00010] In some embodiments, the key identifiers includes names or IDs of the person.
[00011] In some embodiments, the method further includes configuring, a Bluetooth low energy (BLE) integration module, to prevents proxy attendance.
[00012] In some embodiments, the voice input is a predefined phrase which is spoken by the person.
[00013] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein, and the embodiments herein include all such modifications.
BRIEF DESCRIPTION OF THE DRAWINGS
[00014] The embodiments herein will be better understood from the following detailed description with reference to the drawings, in which:
[00015] FIG. 1 illustrates an attendance system using speech recognition, according to some embodiments herein; and
[00016] FIG. 2 illustrates a flow chart showing a method for providing an attendance system using speech recognition, according to some embodiments herein.
DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS
[00017] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
[00018] As mentioned, there remains a need for an attendance system using speech recognition and method thereof. Referring now to the drawings, and more particularly to FIGs. 1 through 2, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments.
[00019] FIG. 1 illustrates an attendance system 100 using speech recognition, according to some embodiments herein. The system 100 includes a voice input receiving module 102, a voice preprocessing module 104, a feature extraction module 106, a text analysis module, a speaker verification module 110, an attendance logging module 112, and an admin interface module 114. The voice input receiving module 102 is configured to record voice from speaker. The voice preprocessing module 104 is configured to preprocess the record voice to remove noise. The feature extraction module 106 is configured to convert raw waveform of the preprocessed recorded voice to text using deep learning models. The text analysis module is configured to extracts key identifiers from the extracted features. The speaker verification module 110 is configured to compares extracted key identifiers with stored profiles. The attendance Logging module 112 is configured to mark an attendance of a person if the key identifiers match with the stored profile of the person. The admin interface 114 module is configured to record the attendance of the person.
[00020] In some embodiments, the key identifiers includes names or IDs of the person. The system 100 further includes a Bluetooth low energy (BLE) integration module 108 that is configured to prevents proxy attendance. The voice input is a predefined phrase which is spoken by the person. In a non-limiting example, the recorded voice format is WAV format. The voice preprocessing module 104 uses Librosa or PyAudio. A Wav2Vec 2.0 converts the recorded voice into text. Amazon Transcribe converts speech to text via AWS’s API. The BLE integration module 108 ensures attendance is logged only within a specific area. The BLE integration module 108 helps track attendance in classrooms or offices. The BLE integration module 108 prevents misuse by confirming physical location before logging. The BLE integration module 108 uses BLE, RFID, Wi-Fi, or cellular data to create a virtual boundary (a "fence") (202). Geofencing ensures that attendance is logged only when users are physically present within a predefined area, such as a classroom or office. This prevents proxy attendance and ensures accurate tracking.
[00021] The system 100 encrypts the sensitive data (like voice samples) before storage. The system 100 only authorized personnel can access the database. Further voice features are hashed to prevent unauthorized use. For example, employees (or the person) speaks a predefined phrase. The system 100 extracts unique voice features. The system 100 compares the unique voice features with stored voiceprints. If authenticated, the system 100 grants access (for example unlocking doors, system login).
[00022] FIG. 2 illustrates a flow chart showing a method for providing an attendance system using speech recognition, according to some embodiments herein. At step 202, the method 200 includes configuring, a voice input receiving module, to record voice from speaker. At step 204, the method 200 includes configuring, a voice preprocessing module, to preprocess the record voice to remove noise. At step 206, the method 200 includes configuring, a feature extraction module, to convert raw waveform of the preprocessed recorded voice to text using deep learning models. At step 208, the method 200 includes configuring, a text analysis module, to extracts key identifiers from the extracted features. At step 210, the method 200 includes configuring, a speaker verification module, to compares extracted key identifiers with stored profiles. At step 212, the method 200 includes configuring, an attendance logging module, to mark an attendance of a person if the key identifiers match with the stored profile of the person. At step 214, the method 200 includes configuring, an admin interface module, to record the attendance of the person.
[00023] An advantage of the system 100 is that the system 100 provides high security. For example, it’s harder to forge than fingerprints or passwords.
[00024] An advantage of the system 100 is that the system 100 provides hands-free access. For example, useful in high-security environments.
[00025] An advantage of the system 100 is that the system 100 can be linked with attendance and payroll systems.
[00026] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practised with modification within the scope of the appended claims.
, Claims:We claim:
1. An attendance system (100) using speech recognition, the system (100) comprising:
a voice input receiving module (102) that is configured to record voice from speaker;
a voice preprocessing module (104) that is configured to preprocess the record voice to remove noise;
a feature extraction module (106) that is configured to convert raw waveform of the preprocessed recorded voice to text using deep learning models;
a text analysis module that is configured to extracts key identifiers from the extracted features;
a speaker verification module (110) that is configured to compares extracted key identifiers with stored profiles;
an attendance logging module (112) that is configured to mark an attendance of a person if the key identifiers match with the stored profile of the person; and
an admin interface module (114) that is configured to record the attendance of the person.
2. The system (100) as claimed in claim 1, wherein the key identifiers comprises names or IDs of the person.
3. The system (100) as claimed in claim 1, wherein the system (100) further comprises a Bluetooth low energy (BLE) integration module (108) that is configured to prevents proxy attendance.
4. The system (100) as claimed in claim 1, wherein the voice input is a predefined phrase which is spoken by the person.
5. A method (200) of proving an attendance system using speech recognition, the method (200) comprising:
configuring (202), a voice input receiving module, to record voice from speaker;
configuring (204), a voice preprocessing module, to preprocess the record voice to remove noise;
configuring (206), a feature extraction module, to convert raw waveform of the preprocessed recorded voice to text using deep learning models;
configuring (208), a text analysis module, to extracts key identifiers from the extracted features;
configuring (210), a speaker verification module, to compares extracted key identifiers with stored profiles;
configuring (212), an attendance logging module, to mark an attendance of a person if the key identifiers match with the stored profile of the person; and
configuring (214), an admin interface module, to record the attendance of the person.
6. The method as claimed in claim 5, wherein the key identifiers comprises names or IDs of the person.
7. The method as claimed in claim 5, wherein the method further comprises configuring, a Bluetooth low energy (BLE) integration module, to prevents proxy attendance.
8. The method as claimed in claim 5, wherein the voice input is a predefined phrase which is spoken by the person.