I successfully defended my PhD on the 29th of September. At the time I was feeling a whirlwind of emotions that were quite difficult to articulate. Now I feel like I am ready to share some more details about that day.
Welcome to the first technical blog post of this page. The goal of this post is to provide a general overview of the evaluation process for a standard Speech Translation (ST) setup. The focus will be on highlighting the differences of the ST setup with the standard Machine Translation (MT) scenario. Thus, the reader should have some basic MT knowledge in order to follow along.
I successfully defended my PhD on the 29th of September. At the time I was feeling a whirlwind of emotions that were quite difficult to articulate. Now I feel like I am ready to share some more details about that day.
I finally bit the bullet and started working on a personal website and blog. The main goal is to highlight interesting topics I have been working on, as well as sharing interesting or useful tidbits I discover during my work. The standard scientific paper is sometimes not the best medium to discuss some of the nuances of one’s research, for example due to the fact that one tends to self-select and show only the most convincing and/or status-quo friendly version of our research as to maximize the chance of publication. Hopefully this format will allow me to shed some light into some of the overlooked or controversial details about research.
I successfully defended my PhD on the 29th of September. At the time I was feeling a whirlwind of emotions that were quite difficult to articulate. Now I feel like I am ready to share some more details about that day.
I have recently released an updated version of my Streaming Text Segmenter software, which I published at the start of my PhD. This was my first “serious” software project, the results were quite nice, and it has played quite an important role for my research and technology transfer activities over these past 3 years. I have grown a lot during this time, so I want to summarize the main changes that I have applied over the years, and what important lessons I learned along the way.
I have recently released an updated version of my Streaming Text Segmenter software, which I published at the start of my PhD. This was my first “serious” software project, the results were quite nice, and it has played quite an important role for my research and technology transfer activities over these past 3 years. I have grown a lot during this time, so I want to summarize the main changes that I have applied over the years, and what important lessons I learned along the way.
Welcome to the first technical blog post of this page. The goal of this post is to provide a general overview of the evaluation process for a standard Speech Translation (ST) setup. The focus will be on highlighting the differences of the ST setup with the standard Machine Translation (MT) scenario. Thus, the reader should have some basic MT knowledge in order to follow along.