Date of Award


Document Type


Degree Name

Master of Science (MS)


Computer Engineering and Sciences

First Advisor

Veton Z. Këpuska

Second Advisor

Fareena Saqib

Third Advisor

Marius C. Silaghi

Fourth Advisor

Samuel P. Kozaitis


This thesis will describe the theoretical background and implementation details of Google Speech Recognition using embedded system. AM37x Evaluation Board developed by Texas Instrument is used as a test bed. All major applications of Google Speech Recognition are covered in this thesis. Also, Evaluation of Google Speech API based on standard dataset is also part of the thesis.

Each implementation details are included with the theoretical background and pre-requisite details:

  • Overview of the background of Automatic Speech Recognition Technology.
  • Overview of Google Speech Recognition.
  • Overview of AM37x Evaluation Module.
  • Drivers and Android OS upgradation details.
  • Installation of Google pre-requisite Apps on AM37x.
  • Implementation details of experiment i.e. Speech to Text, Text to Speech and Audio File to Speech.
  • Evaluation of Google Speech API using TIMIT.