Company Website

Jadwin, MO

Big Rock Candy Mountain Company Website

Worked with the owners to design and develop a website to replace the companies' old website. I utilized GatsbyJS coupled with the Contentful CMS to build a modular site to allow the users to have direct control over adding and removing content and information. As well an integration with Google Calendar to allow events to populate on to the website without reentry.

Resume Site

Springfield, MO

Resume Website

I developed this website as a learning experience and as a place to house my resume and showcase projects I have completed. This website is built using NextJS for the primary app as well as the API server. The API server interacts with a cloud based Mongo database which stores all the portfolio data. The front-end also contains an interface which allows authenticated users to write and edit entries in the database. Authentication is handled by Auth0.

Conference Paper

2022 IEEE 46th Annual Computer, Software, and Applications Conference (COMPSAC)

Multi-Scale Speaker Vectors for Zero-Shot Speech Synthesis

In this paper, we propose a novel speaker encoder model utilizing some of those techniques, such as self-attention and transformers. The proposed model results in a speaker embedding vector called Multi-Scale Speaker (MSS) vectors. MSS vectors aim to make improvements over the current state-of-the-art speaker embeddings for more natural and similar-sounding synthesized speech for unseen speakers in a zero-shot speech synthesis model. The proposed architecture relies on encoder layers which are coupled with a multi-scale approach for learning both local and global mel-spectra features of a reference speaker.

Conference Paper

IEEE 46th International Symposium on Multimedia (ISM)

Comparison of Multi-Scale Speaker Vectors and S-Vectors for Zero-Shot Speech Synthesis

We compare a novel speaker encoder model, called Multi-Scale Speaker (MSS) Vectors, with state-of-the-art s-vectors model for zero-shot speech synthesis. The s-vectors model relies on a modified transformer self-attention network for its architecture. The MSS vectors model introduces a multi-scale approach to the s-vectors model. Results demonstrate that our model produces more natural and similar-sounding synthesized speech for unseen speakers in a zero-shot speech synthesis system.