A Practitioner’s Look at Speech -to-Text

Posted in News Story  |  Tagged

Mark Dickison, Technical and Modeling Lead for Capital One’s internal speech recognition team – SpeakEasy


This talk covers the basics of Speech-to-Text using Hidden Markov Models and Gaussian Mixture Models (HMM-GMM). Included will be a discussion of the basics of signal processing for speech recognition, acoustic and language models, and how they are jointly maximized to produce text.

​ As time and interest allows, Neural Networks, and how they can be used either in hybrid with HMM-GMM models will also be covered.


Mark Dickison started his career as a computational physicist specializing in network science – acquiring his Ph.D. from Boston University. This was followed by a post-doctoral fellowship at Pennsylvania State in their USP program, which supports the US Defense Threat Reduction Agency. Leaving academia, he joined Booz Allen Hamilton as a data scientist, working with a variety of clients across health, finance, and energy. Mark is currently the Technical and Modeling Lead for Capital One’s internal speech recognition team – SpeakEasy.

View “A Practitioner’s Look at Speech-to-Text” Presentation

More Analytics Seminars

Student Perspective: Torqata Reinvent the Wheel Hackathon

February 2nd, 2023

Participating in a Hackathon is an important milestone in any data scientist’s journey. Hackathons provide an exciting opportunity to take the skills and techniques you’ve learned and apply them to solving a challenging business problem for a company.…

DSAN Partners with Lander Analytics for R Gov Conference

December 15th, 2022

The first two days of December saw DSAN partnering with Lander Analytics to host the R Gov Conference. The R Gov Conference hosts one of the most elite gatherings of data scientists and data professionals who come together to explore, share, and inspire ideas, and to promote the growth of open-source ideals.…

DSAN and DataKindDC Partner for a DataDive for Social Impact

November 7th, 2022

On Saturday, October 22, we partnered with DataKindDC for an all-day data dive, giving our students a chance to work in real-time alongside local volunteer data scientists on projects for four non-profits to move the selected organization’s programming forward and benefit the communities they serve.…