Find Jobs
Hire Freelancers

speech recognition platform

$250-750 USD

Inaendelea
Imechapishwa over 3 years ago

$250-750 USD

Kulipwa wakati wa kufikishwa
I would like to offer you a job that involves developing a speech engine for urdu language. I can share details latter if you are interested. details are as follows; Training Acoustic Model (AM) Goal: Train Urdu AM by hybrid HMM (Hidden Markov Model) & DNN Steps and Deliverables: - Analysis acoustic feature: calculate MFCC (Mel Frequency Cepstrum) and do CMVN (Cepstrum Mean Variance Normalization) for noise-robust. (feature vectors files) - VAD: Voice Activity Detection(DNN based VAD or other).(VAD model and vad result) - Train HMM AM and align feature vectors. (mono-phone HMM and Triphone HMM dictionary) - Train LDA (Linear Discriminate Analysis) and MLLT(Maximum Likelihood Linear Transform) matrices.(transform matrices) - Train fMLLR (frame-based Maximum Likelihood Linear Regression) and SAT (Speaker Adaptation Transform) matrices. (transform matrices) - Next, get the alignment for DNN AM training. (basic data for DNN training) - Train TDNN (Time Delay NN) & LSTM (Long short-term memory) NN.(DNN model file) In this step, we can test various DNN architectures for the best performance. Decoding Urdu speech by the trained DNN AM and LM. Goal: Construct Urdu speech recognition system by the trained DNN and test its performance. Steps and Deliverables: - Read test wave file and analysis MFCC features. - VAD and CMN - search the best path on lattice. - evaluate the performance of Urdu STT. Budget: $1000 The deadline is 2 weeks max and expected accuracy is above 90%
Kitambulisho cha mradi: 27466988

Kuhusu mradi

6 mapendekezo
Mradi wa mbali
Inatumika 4 yrs ago

Unatafuta kupata pesa?

Faida za kutoa zabuni kwenye Freelancer

Weka bajeti yako na muda uliopangwa
Pata malipo kwa kazi yako
Eleza pendekezo lako
Ni bure kujiandikisha na kutoa zabuni kwa kazi
6 wafanyakazi huru wana zabuni kwa wastani $437 USD kwa kazi hii
Picha ya Mtumiaji
Hi, I see that you need some assistant in I am expert and having 5 years of experience in simulations using MATLAB and SIMULINK in many fields including Electronics, Communication, Control System, Signal Processing and Mathematics etc.I can help you with anything related to Electrical engineering. Udemy / Skillshare Certified: Simulations and Coding using Matlab/Simulink: 1) Linear Algebra, Calculus and Numerical Methods with coding 2) Electrical Power System Design And Simulation 3) Digital Signal Processing 4)Control System Design and Simulation 5) Image Processing 6) communication systems design and simulation I can provide services: 1 Image classification, Machine Learning, and such other stuff 2 Image processing in Matlab including medical Image Processing 3 GUI (Graphical User Interface) 4 Paper presentation 5 Computer vision 6 Speech and audio processing in Matlab 7 Brain signal processing 8 Digital signal processing in Matlab, I'll be cheerful in case you can trust in me to assist you with this endeavor. You can enlist me straightforwardly through this connection. Below is my profile, you can check my past works and review. https://www.freelancer.com/u/mzdesmag?w=f
$250 USD ndani ya siku 2
4.9 (9 hakiki)
4.8
4.8
Picha ya Mtumiaji
Greetings , I have completely comprehended the description. I am a proficient Artificial & Deep learning programmer with 3+ years of experience. I can surely full fill your conditions under a significant and affordable budget. Consider me once & you will be overwhelmed with my services. I appreciate your time for reading this. I am looking forward to your response
$250 USD ndani ya siku 7
4.6 (6 hakiki)
4.9
4.9
Picha ya Mtumiaji
Thanks for the opportunity to provide a proposal. As I have 6+ years of experience in Machine Learning, Deep Learning, Python, Data Mining, Tensorflow, OpenCV and I provide you high-quality work, and reasonable rates and I have read all the requirements and I am ready to work with you. Can we discuss this more?
$250 USD ndani ya siku 7
5.0 (2 hakiki)
3.8
3.8
Picha ya Mtumiaji
I am an experienced python developer, with remarkable projects. One of my best project was my final year project on speaker identification system. The system used tensorflow speech data, and self recorded wav files and other recorded wav files. I used mfcc to extract the mel features, then developed melspectrograms. I used the spectrograms as image data for convolutional neural network. Based on your requirement I believe I am best suited to developing the model for you. The model can still be built using hidden markov model and other models.
$920 USD ndani ya siku 7
0.0 (0 hakiki)
0.0
0.0
Picha ya Mtumiaji
Hi, I have a good experience in machine learning and deep learning. Also I have some knowledge in speech recognition using sphinx and kaldi that support your requirements about using HMM and DNN to train the Acoustic Model and Language model. Also I have some knowledge about End-To-End process using deep learning, if you want. Waiting your contact to discuss the details.
$500 USD ndani ya siku 7
0.0 (0 hakiki)
0.0
0.0
Picha ya Mtumiaji
Hi am an aspiring data scientist since last one year. I am working on various types of Machine Learning Algorithms and started working on deep learning projects and i am able to work like that projects. If u award me this project then I will make sure that this will a good project.
$450 USD ndani ya siku 10
0.0 (0 hakiki)
0.0
0.0

Kuhusu mteja

Bedera ya PAKISTAN
Karachi, Pakistan
5.0
1
Njia ya malipo imethibitishwa
Mwanachama tangu Mac 26, 2020

Uthibitishaji wa Mteja

Asante! Tumekutumia kiungo cha kudai mkopo wako bila malipo kwa barua pepe.
Hitilafu fulani imetokea wakati wa kutuma barua pepe yako. Tafadhali jaribu tena.
Watumiaji Waliosajiliwa Jumla ya Kazi Zilizochapishwa
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2024 Freelancer Technology Pty Limited (ACN 142 189 759)
Onyesho la kukagua linapakia
Ruhusa imetolewa kwa Uwekaji wa Kijiografia.
Muda wako wa kuingia umeisha na umetoka nje. Tafadhali ingia tena.