Closed

Speech Recognition/Speech Analytics Design

This project is to determine the feasibility of a larger project involving speech recognition. We want to determine if it is feasible to build our our "speech analytics" capability using an open source project.

We are a call recording company that records calls for call centers. Many of our clients are interested in the ability to convert the recorded conversation into words that can be searched, counted, summarized and reported. This requires large vocabulary, speaker-independent speech recognition, either in the form of phoneme recognition or word recognition. There are a number of commercial software capabilities to do this, but we want to see if we can build the same ourselves.

There are two open source projects we are interested in working with: Julius and Sphynx. You should only bid on this project if you are familiar with those or something very similar (e.g. RWTH ASR).

The deliverable for this project is a design that shows how to use the available to software (including supporting software to be created) to do the following:

1) Build an acoustic model for the call center's recordings. Assume we will have a large sample of audio recorded and can have it transcribed as needed.

2) Take each individual recording and process it through a recognition engine (we are assuming the use of stereo recordings in which we can process the speech of each party on the call separately.)

3) Generate a set of words or phonemes from the processing and store in a file that will be used for searching and reporting.

Depending on the response, we may award the project to multiple bidders to determine the best design. The bidder with the best design is most likely to then be awarded the project to develop the full system.

Do not bid unless you have a good understanding of speech recognition technology and the open source projects listed above. You will wasting your time and mine if you bid and do not have expertise in this area.

Skills: C++ Programming, Java

See more: phoneme recognition open source, understanding programming, stereo design, searching java, sample bid response, programming vocabulary, programming expertise, programming center, java open source programming, design vocabulary, cplusplus set, call center technology, call center number, best java programming software, best java programming, best design software, audio commercial, asr software, speech recognition software, project speech recognition, speech recognition open source, it vocabulary, stereo, speech recognition, software recognition

About the Employer:
( 81 reviews ) Charlotte, United States

Project ID: #1097900

15 freelancers are bidding on average $3920 for this job

asrlabs

ASR Labs provides professional automatic speech recognition services. We develop software, grammars, phonetic dictionaries, language models and related topics in American English, Brazilian Portuguese and Latin America More

$10000 USD in 120 days
(0 Reviews)
0.0
mehmetalikara

Dear Employer, We have a software team consists of professionals Most of us have 10+ years software development experience. We are using the most popular and efficient frameworks and development methodologies. We More

$15000 USD in 90 days
(0 Reviews)
0.0
itresolvers

We can do this project sir. We have done these kind of assignments already

$2000 USD in 30 days
(0 Reviews)
0.0
Altisinfotech

We are interested in this project. We have already develop a project on voice commands

$1500 USD in 30 days
(0 Reviews)
0.0
yunusbtech

Requirement Software > Dotnet framework 2.0 Hardware > PC and mic Discription: > Just run application exe > start voice input > speak input through mic Note: your matched voice input automaticall More

$1500 USD in 10 days
(0 Reviews)
0.0
fahedprince

Please check your PMB

$1000 USD in 30 days
(0 Reviews)
0.0
mic4m

Please check PM

$1500 USD in 60 days
(0 Reviews)
0.0
CSivaRam

Hi, We would be able to provide the solution. We have worked on speech recogntion software in matalb where in we map voices and give a textual representation in terms of phonetics. We require 50 Days so tha More

$10000 USD in 50 days
(0 Reviews)
0.0
ajaykumar0005

1. language:java description: i am making calculator,which works on speech. In this project i also used the technology speech synthesis.

$1000 USD in 20 days
(0 Reviews)
0.0
paployan

Hello, we are interested in your post. Our team members are under the mentoring of seasoned C++ expert will do their best to get you satisfied. I'm sure it would be very interesting collaboration for both of us. We More

$3000 USD in 90 days
(0 Reviews)
0.0
jacktendi

please check pmb for our bid

$800 USD in 5 days
(0 Reviews)
0.0
stdcall

I would be glad to work on this project.

$5000 USD in 31 days
(0 Reviews)
0.0
zoint

I can make this project on MATLAB environment.I have a project about this point.But it is so simply forming.(your project is complex than mine)If you want to other languages(c and java),I can do it.Meanwhile,I'm workin More

$3000 USD in 45 days
(0 Reviews)
0.0
jrunner

Dear sir, we are a group of expert on pattern matching and machine learning field. We can confirm you to deliver the best quality product on due time. Thank you.

$2000 USD in 15 days
(0 Reviews)
0.0
MasterOfMachines

Please read my pm!

$1500 USD in 15 days
(0 Reviews)
0.0