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.
This project is designed for learning purposes and is not a complete, production-ready application or solution.
liveProject mentor Stefano Masneri shares what he likes about the Manning liveProject platform.
When you start your liveProject, you get full access to the following books for 90 days.
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.
This liveProject is for confident Python programmers with existing experience in machine learning. It will hone your skills for handling the uncommon audio data type, and constructing deep learning pipelines. To begin this liveProject, you will need to be familiar with:
Basics of data analysis
Basics of supervised machine learning
Classification problems and suitable quality metrics
Supervised training of artificial neural networks
you will learn
In this liveProject, you’ll master foundational skills in audio data processing that provide an excellent starting point for voice-controlled assistants, conversational UIs, and other speech apps.
Audio processing with Python
Representing audio data
Feature engineering for machine learning with audio
Computing and visualizing spectrograms
Convolutional neural network architectures for audio
GPU-accelerated deep learning
You choose the schedule and decide how much time to invest as you build your project.
Each project is divided into several achievable steps.
While within the liveProject platform, get help from other participants and our expert mentors.
Compare with others
For each step, compare your deliverable to the solutions by the author and other participants.
Get full access to select books for 90 days. Permanent access to excerpts from Manning products are also included, as well as references to other resources.