Speech Application Engineer

GO-VIVACE, INC.
Tysons, United States of America
6 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English, Hindi

Job location

Tysons, United States of America

Tech stack

Artificial Intelligence
Amazon Web Services (AWS)
Artificial Neural Networks
Automation of Tests
C++
Nvidia CUDA
Continuous Integration
Text Processing
Perl
Github
Python
Machine Learning
Language Modeling
Natural Language Processing
Performance Tuning
Shell Script
Speech Recognition
Transfer Learning
Parallel Computation
Low Latency
Bitbucket
Natural Language Understanding
Software Version Control
Jenkins
Programming Languages

Job description

We are looking for a Speech application engineer, who is efficient in programming languages like Python, c++, Perl, Shell script, with good knowledge in practical Speech-to-Text and Natural Language Processing systems., 01.Training and optimizing acoustic and language models for Indian languages Automatic Speech Recognition (ASR). 02.Parameters tuning and optimization of latency and accuracy of ASR applications.

  1. Tuning and deploying Deep Neural Network-based Speech-to-text models that are customized and optimized as per clients' requirements.
  2. Implementing and researching new innovative ideas in the domain of Speech technology which could enhance the accuracy and speed of our ASR and NLU systems.
  3. Maintaining and writing Shell scripts for end-to-end training and testing of ASR models for various project deployments.
  4. Preparing and cleaning of data resources and transcripts used for training ASR models.
  5. Exploring and implementing cutting-edge Artificial Intelligence and Machine learning techniques like Transfer learning, Multi-task training, especially in low data resource scenarios like for Indian languages ASR.

Requirements

Do you have experience in Version control systems?, 01. Strong proficiency in C++, Python, Perl and shell scripting with efficient coding style.

  1. Code version control and continuous integration testing tools like Github, Jenkins, bitbucket.
  2. Implementation of real-time low latency Speech-to-text systems in telephony and IVR domain, Natural Language processing workflows, knowledge of Kaldi ASR toolkit is a plus.
  3. Sound knowledge of Machine learning algorithms and basics.
  4. Experience with Parallel computing environments like CUDA, and grid-engines or AWS instances is a plus.

Technical skills: C++, Python, Perl and shell scripting Machine learning Natural Language and text processing

Apply for this position