Page 306 - AWSAR 2.0

282 || AWSAR Awarded Popular Science Stories - 2019
Automatic Spoken Language Recognition Systems for Indian and Oriental Languages Using Digital Speech Signal Processing and Machine Learning Approaches
Mr. Nettimi Satya Sai Srinivas*
Email: satya_srinivasnettimi@live.com
Speech recognition is an interdisciplinary research field that includes Digital Speech Signal Processing, Machine Learning,
and Computational Statistics. It refers to the process of recognizing distinct information from the speech signal. Current technology allows us to recognize and to extract different information from the speech signal. The type of information recognized can be put into actual use for solving several interesting research problems. Examples of potential applications using speech-based recognition systems in real-time environments are listed as follows: The speech-based recognition systems can recognize (1) speaker characteristics (identity, gender, emotional state), (2) spoken content by the speaker (control/command words, continuous speech, language), (3) medical
diagnostic characteristics (voice abnormalities, pathologies, and other conditions like cough), and many more. In a broader sense, the field of speech recognition deals with the design and development of methodologies and technologies, which are capable enough to establish a natural man-machine interaction. Speech technology aims to simplify the way in which humans interact with the machines. Nowadays, the rapid advancements in technology enable humans to use their speech to communicate and to control the machines. In order to achieve this, the modern machines are equipped with built-in mechanisms, to recognize and to understand the human intentions conveyed in their speech, and lets them to take appropriate actions. Despite the great progress made in this field, the natural
* Mr. Nettimi Satya Sai Srinivas, PhD Scholar from National Institute of Technology, Puducherry, is pursuing his research on “FPGA Prototype for Automatic Speech Recognition System using Machine Learning-Based Classification Algorithms”. His popular science story entitled “Automatic Spoken Language Recognition Systems for Indian and Oriental Languages using Digital Speech Signal Processing and Machine Learning Approaches” has been selected for AWSAR Award.