Find Jobs
Hire Freelancers

Lie Detection in speech using Machine Learning

₹1500-12500 INR

Kansellert
Lagt ut omtrent ett år siden

₹1500-12500 INR

Betalt ved levering
The proposed method uses acoustic features in speech, such as Mel-frequency cepstral coefficients (MFCC), energy envelopes, and pitch contours for training a recurrent neural network to detect lies. This project aims to train a deep learning network using audio characteristics from call recordings for lie detection. The sound characteristics that will be used for training are pitch contours, energy envelopes and Mel-frequency cepstral coefficients (MFCC), which are produced from a training set of deceitful and non-deceitful recordings. Reportedly, more than 202 million spam calls were made from just one phone number between January and October of this year. Thus, the project also aims to answer the true intention of callers posing as bank and network operators phishing for valuable customer data. An automated lie detection system based on acoustic features in speech can help expose such dangerous callers and help in keeping our data secure.
Prosjekt-ID: 36515093

Om prosjektet

5 forslag
Eksternt prosjekt
Aktiv ett år siden

Ønsker du å tjene penger?

Fordeler med budgivning på Freelancer

Angi budsjettet og tidsrammen
Få betalt for arbeidet ditt
Skisser forslaget ditt
Det er gratis å registrere seg og by på jobber
Tildelt til:
Brukeravatar
I'm a data scientist with 6 years of experience in developing machine learning models, worked on both video and audio models and have done my masters in machine learning.. With my extensive background as a data scientist, I am confident in my ability to deliver a high-quality solution that meets your objectives. My approach to this project involves training a deep learning network using audio characteristics extracted from call recordings. By leveraging the sound characteristics present in the pitch contours, energy envelopes, and MFCC coefficients, the lie detection system will be trained on a comprehensive dataset of deceitful and non-deceitful recordings. Below is my proposal: 1. I will carefully curate a dataset of call recordings encompassing both deceitful and non-deceitful recordings 2. Utilizing signal processing techniques, will extract essential acoustic features from the call recordings. 3. I will design and implement a RNN architecture tailored for sequence classification. 4. Using the collected dataset, I will train the RNN model while continually evaluating its performance on validation sets. 5. Once the model achieves satisfactory results, I will deploy it into a real-time system, allowing for seamless classification of incoming audio as truthful or deceptive. By entrusting this project to me, you can be assured of my commitment to delivering an effective lie detection system. Looking forward to the opportunity to collaborate on this important project.
₹8 000 INR om 7 dager
0,0 (1 omtale)
0,0
0,0
5 frilansere byr i gjennomsnitt ₹8 900 INR for denne jobben
Brukeravatar
Hi there, I am an ML engineer. I can start right away and deliver within the deadline. So, Let’s have a quick conversation. I can be more specific once we get all the requirements and information required to execute the project. Thank you!!
₹12 500 INR om 7 dager
5,0 (43 omtaler)
5,2
5,2
Brukeravatar
Hello, I am very familiarized with the requirements of your projects. And it can be done really fast. Let's connect over chat to discuss more on this. Thanks
₹7 000 INR om 7 dager
5,0 (5 omtaler)
3,2
3,2
Brukeravatar
Hi, ⭐⭐⭐It's me you're looking for.⭐⭐⭐ Hi, there. ⭐⭐⭐ I would like to ask few questions before start your project ⭐⭐⭐ ⭐⭐⭐ I will give you exact quote after detailed discussion ⭐⭐⭐ I am a specialist with 7 years proven experience in Full-Stack development. As per your project need, I can build your project more efficient with my knowledge and experience. I have checked your project description thoroughly and I think that I can help you to complete this project fully 100% sure to satisfy your requirement. If you leave it up to me, I will be able to implement this project perfectly & smartly ⭐ASAP⭐. So please don't hesitate to contact me and share more details about your project specs in chat. Everything is negotiable. Thanks and Regards.
₹7 000 INR om 7 dager
5,0 (1 omtale)
0,8
0,8

Om klienten

INDIAs flagg
India
0,0
0
Betalingsmetode bekreftet
Medlem siden mai 4, 2023

Klientbekreftelse

Takk! Vi har sendt deg en lenke for at du skal kunne kreve din gratis kreditt.
Noe gikk galt. Vær så snill, prøv på nytt.
Registrerte brukere Publiserte jobber
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2024 Freelancer Technology Pty Limited (ACN 142 189 759)
Forhåndsvisning innlasting
Tillatelse gitt for geolokalisering.
Påloggingsøkten din er utløpt og du har blitt logget ut. Logg på igjen.