Papers by Javier Iranzo-Sánchez
From Simultaneous to Streaming Machine Translation by Leveraging Streaming History (2022.acl-long)
Copied to clipboard
| Challenge: | Streaming MT is an extension of simultaneous MT to the incremental translation of a continuous input text stream. |
| Approach: | They propose to extend simultaneous machine translation to streaming setups by leveraging streaming history. |
| Outcome: | The proposed system compares favorably to the best performing systems on IWSLT Translation Tasks. |
Stream-level Latency Evaluation for Simultaneous Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Simultaneous machine translation systems need to find a trade-off between translation quality and response time. |
| Approach: | They propose to adapt existing translation latency measures to streaming scenarios by re-segmenting the output translation to take into account sequential nature of streaming scenarios. |
| Outcome: | The proposed measures are evaluated on a streaming task on simulated speech translation systems. |
Direct Segmentation Models for Streaming Speech Translation (2020.emnlp-main)
Copied to clipboard
Javier Iranzo-Sánchez, Adrià Giménez Pastor, Joan Albert Silvestre-Cerdà, Pau Baquero-Arnal, Jorge Civera Saiz, Alfons Juan
| Challenge: | Existing approaches to stream ST combine advances in ASR and MT to achieve high quality translations without compromising the speed of the system. |
| Approach: | They propose to concatenate an Automatic Speech Recognition system followed by a Machine Translation system. |
| Outcome: | The proposed models improve on the Europarl-ST dataset on the BLEU score. |
VivesDebate-Speech: A Corpus of Spoken Argumentation to Leverage Audio Features for Argument Mining (2023.emnlp-main)
Copied to clipboard
| Challenge: | a corpus of spoken argumentation is used to leverage audio features for argument mining tasks . a vast majority of arguments-based natural language processing resources only take text features into account . |
| Approach: | They describe a corpus of spoken argumentation created to leverage audio features for argument mining tasks. |
| Outcome: | The proposed corpus of spoken argumentation improves when integrating audio features into the argument mining pipeline. |
Going Beyond Your Expectations in Latency Metrics for Simultaneous Speech Translation (2025.findings-acl)
Copied to clipboard
| Challenge: | Current evaluation practices in Simultaneous Speech Translation systems involve segmenting the input audio and its translations, calculating quality and latency metrics for each segment, and averaging the results. |
| Approach: | They propose to use the mean to estimate latency for Simultaneous Speech Translation systems to provide a better understanding of their results. |
| Outcome: | The proposed methods can provide a better understanding of SimulST systems’ latency. |