Vamsi Sistla

Vamsi Sistla is a proven leader in data science and applied AI. He has experience in managing large-scale projects and teams in data engineering, ML operations, and ML modeling. He has helped in developing and implementing enterprise AI strategy. He has experience in building distributed machine learning workflows using Apache Spark, DASK, Rapids and Kubernetes.

Currently, he is working at Nike, Inc. as Director of Reusable Features and ML Models. In the past he has done 2 startups, and also has a master’s in data sciences (MIDS) from the University of California, Berkeley.

projects by Vamsi Sistla

Recognize Speech Commands with Deep Learning

4 weeks · 3-5 hours per week · INTERMEDIATE

Included with a Manning Online subscription

catalog / Data Science

Voice assistants and speech-based applications need a reliable understanding of human commands. Deep learning systems trained on audio data are a great way for models to learn directly from sound and easily classify what humans are telling them.

In this liveProject, you’ll become a data scientist prototyping a speech command system for a medical organization. Your company’s application will allow hospital patients to adjust their room TVs with their voice, and you’ve been tasked with building the core: a machine learning pipeline that can label audio inputs with given command words. You’ll tackle preprocessing and feature engineering methods for audio signals, expand your existing machine learning capabilities with audio data, and get hands-on experience with TensorFlow, Keras, and other powerful Python deep learning tools.