Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About - Javier Iranzo-Sánchez
About me
Page not in menu
This is a page not in th emain menu
Posts
My PhD Thesis Defense
Published:
PhD Defense
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.
Lessons learned from developing research software: Updating the Streaming Segmenter
Published:
Introduction
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.
An overview of Speech Translation Evaluation
Published:
Introduction
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.
Welcome to my web page: Motivation
Published:
Hello world!
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.
portfolio
Portfolio item number 1
Published:
Short description of portfolio item number 1
Portfolio item number 2
Published:
Short description of portfolio item number 2
publications
Europarl-ST: A Multilingual Corpus for Speech Translation of Parliamentary Debates
Published in ICASSP, 2020
Speech Translation datasets are a scarce resource, and this greatly hampers research in the area. Europarl-ST, first released in 2019, was a game-changer for Speech Translation research, thanks to the wide range of languages covered and a careful filtering pipeline. Currently (early 2023), close to 100 publications have cited Europarl-ST.
Direct Segmentation Models for Streaming Speech Translation
Published in EMNLP, 2020
Machine Translation systems are trained with full sentences, but in the Cascaded Speech Translation scenario, the output of the ASR system does not necessarily form sentences, which hampers performance. This publication introduces a streaming-ready segmenter applied to the output of the ASR system, in order to maximize downstream translation quality.
Streaming cascade-based speech translation leveraged by a direct segmentation model
Published in Neural Networks, 2021
This paper extends the previous one (EMNLP2020) with additional experiments and by moving from a simulated Streaming scenario, which used an offline MT system, to a real streaming scenario with a simultaneous MT system.
Stream-level Latency Evaluation for Simultaneous Machine Translation
Published in Findings of EMNLP, 2021
A reliable evaluation metric is critical for any technical and scientific task. However, the standard simultaneous MT latency metrics (AP, AL and DAL) are not robust when applied to the Streaming scenario. This paper studies this phenomenon and proposes a re-segmentation solution that provides reliable and interpretable results for the Streaming scenario.
From Simultaneous to Streaming Machine Translation by Leveraging Streaming History
Published in ACL, 2022
The Streaming ST scenario presents many challenges, but there are also opportunities that can be used to improve translation quality. This work introduces the concept of Streaming history, which holds the information of the previously translated segments. The proposed MT system is able to leverage this contextual information in order to improve translation quality.
talks
Towards Streaming Speech Translation
Published:
On this talk I gave an overview of how Speech Translation is carried out at MLLP research group, with a focus on the MT side.
Unfortunately, the talk was not recorded due to a technical issue, but you can access the slides here.
Towards Streaming Speech Translation - SIGSLT
Published:
This talk provides an overview of the Speech Translation task and its particularities. I then go into detail explaining two contributions of my thesis: 1) a procedure for Streaming ST evaluation, and 2) streaming-specific models with streaming history.
This talk goes into greater detail than my previous one at UPC, so you should definitely watch this one if you interested in Streaming Speech Translation.
The talk is available on Youtube, and you can access the slides here.
My Thesis Defense: Streaming Neural Speech Translation
Published:
This is the presentation of my PhD Thesis. I speak more about this in one of my blog posts. The actual presentation was not recorded, but I sat down a couple of days later and tried to recreate it as best as possible. You can find the video here.