AUTOMATIC SPEECH RECOGNITION

Voice recognition with smart phone.
16
Aug

When: 24th to 25th July 2020

Course Description

Developing and understanding Automatic Speech Recognition (ASR) systems is an inter-disciplinary activity, taking expertise in linguistics, computer science, mathematics, and electrical engineering.

When a human speaks a word, they cause their voice to make a time-varying pattern of sounds. These sounds are waves of pressure that propagate through the air. The sounds are captured by a sensor, such as a microphone or microphone array, and turned into a sequence of numbers representing the pressure change over time. The automatic speech recognition system converts this time-pressure signal into a time-frequency-energy signal. It has been trained on a curated set of labeled speech sounds, and labels the sounds it is presented with. These acoustic labels are combined with a model of word pronunciation and a model of word sequences, to create a textual representation of what was said.

Instead of exploring one part of this process deeply, this course is designed to give an overview of the components of a modern ASR system. In each lecture, we describe a component’s purpose and general structure. In each lab, the student creates a functioning block of the system. At the end of the course, we will have built a speech recognition system almost entirely out of Python code.

Course Content

Total learning: 51 lessons Time: 4 days

Instructor

Arun Panayappan is the Founder of Techcovery Solutions which has been in the training and consulting business for three years now. Arun Panayappan was the Vice President, Platform Engineering at www.goibibo.com which is India’s largest online travel agent. He has over 23 years of IT experience including 4 years of overseas experience.Techcovery has trained over 1000 participants in Data science and mentored 4 start ups during its existence. He has worked as a consulting CTO for companies like cogknit semantics, FirstIPO and Trip38. He is frequently consulted for data science architecture and strategy by corporations across the industry. In his role at Amazon, his technical decision-making skills enabled Kindle Topaz Operations Console to go global and scale seamlessly to meet seasonal load. He drove initiatives to hire and develop the best for the Category Expansions team that doubled in size during his leadership tenure while launching 70 new stores for www.amazon.com every year. He built highly scalable web crawling systems to monitor price changes at competitor sites for millions of products sold by Amazon. This system used statistical machine learning and modeled crawl frequencies using poison distribution. His team built the on-boarding experience of vendor platform(https://vendorexpress.amazon.com) to onboard and manage small and medium size vendors to increase selection and buying options. Prior to joining Amazon, he worked for Kuliza (www.kuliza.com), young start up by ex-Amazon employees, and had served the Research team at Accenture Technology Labs., India. He is an innovative and a tech-savvy leader. He sets a high bar for himself and his team on software design, quality and processes. He has a pleasing personality and excellent communication skills.

Free