The MLLP research group of VRAIN, Universitat Politècnica de València is happy to be at @INTERSPEECH2021 with two articles: 1) Towards simultaneous machine interpretation: dx.doi.org/10.21437/Inter… 2) Europarl-ASR: dx.doi.org/10.21437/Inter…

Don't forget to visit the #Europarl_ASR website to download this new 1300-hour English-language ASR corpus: mllp.upv.es/europarl-asr

New MLLP article in the IFAC_Control journal #EngineeringApplicationsOfAI: “Towards cross-lingual #VoiceCloning in higher education”, by Alejandro Pérez et al. #TextToSpeech to improve accessibility and bridge language barriers. Read all about it: mllp.upv.es/new-mllp-artic…

#BlizzardChallenge2021 results validate the MLLP's scientific research in #TextToSpeech system development. The MLLP's neural TTS synthesis system by Alejandro Pérez et al. obtained excellent naturalness and intelligibility results. Read all about it here: mllp.upv.es/blizzard-chall…

Vicente Fuster comparte en Panorama cómo funciona el sistema de transcripción para directos y diferidos de À Punt. À Punt Universitat Politècnica de València #broadcast #transcripción #accesibilidad panoramaaudiovisual.com/2021/12/02/a-p…

TV #SpeechToText: New report in Panorama Audiovisual provides updated information about À Punt-MLLP project on computer-assisted subtitling for live and pre-recorded broadcast media. Read all about it: mllp.upv.es/new-report-in-…

We're happy to announce the 3rd edition of the simultaneous shared task at IWSLT ! Novelty this year: en-de/en-ja/en-zh, en-de manual eval and human interpretation benchmark, text-to-text and speech-to-text evaluated together. Consider participating! iwslt.org/2022/simultane…

📢 Shared task announcement: IWSLT is running its first task on speech-to-speech translation this year! The task extends the MuST-C dataset with synthesized target speech for parallel S2S data. Interested in speech translation? Consider participating! iwslt.org/2022/speech-to…

Happy to announce the acceptance at #ACL2022 of the article by MLLP member Javier Iranzo-Sánchez "From Simultaneous to Streaming Machine Translation by Leveraging Streaming History". Significant quality gains are shown on IWSLT Translation tasks. Preprint coming soon! ACL 2026

An interesting paper from #EMNLP2021 about latency metrics in real-world scenarios, in which a more interpretable stream-level evaluation is proposed for simultaneous machine translation. MT Group at FBK aclanthology.org/2021.findings-…

We just published the list of papers accepted at IWSLT 2022 iwslt.org/2022

MLLP researchers Javier Iranzo-Sánchez and Javier J will be at #IWSLT2022 to present our article "MLLP-VRAIN UPV systems for the IWSLT 2022 Simultaneous Speech Translation and Speech-to-Speech Translation tasks". Hope to see you there! iwslt.org/2022/papers IWSLT

Javier Iranzo-Sánchez Javier J IWSLT In this paper we present our streaming-ready #ASR, #MT and #TTS systems for #SpeechTranslation and Synthesis from English into German, combined by means of a cascade approach paying special attention to data preparation and decoding for streaming inference.

The ABCD of equitable AI for automatic speech recognition! apptek.com/post/the-abcds…

Dr. Parnia Bahar together with the ⁦AppTek⁩ team (Steve Cook, Mike Veronis & Adria Martinez) at AMTA Orlando 2022 amtaweb.org will present “Spoken MT in Automatic Video Dubbing”

Last year, we published aclanthology.org/2021.findings-…, showing how to adapt the classic AP/AL/DAL metrics to the streaming scenario (unsegmented input). We have now updated the software used in the paper into a package for streaming evaluation, available at github.com/jairsan/Stream…

I recently created a personal website in order to share insights into my research, as well as other topics of interest. You can access it at jairsan.github.io, as well as reading my motivation behind this move here: jairsan.github.io/posts/2012/08/…

The MLLP's Javier Jorge Cano Javier J has earned his PhD in Computer Science at Universitat Politècnica de València, on the topic "#StreamingAutomaticSpeechRecognition with Hybrid Architectures and Deep Neural Network Models". Congratulations, Javi! 🎓 Read all about it: mllp.upv.es/mllp-member-ja…

How should you conduct Speech Translation Evaluation? My latest blog post provides a brief overview that goes beyond pre-segmented academic datasets. This could be specially interesting if you are a newcomer to the field. jairsan.github.io/posts/2022/11/…

Pau Baquero has earned his PhD in Computer Science at Universitat Politècnica de València, on the topic "Transformer models for Machine Translation and Streaming Automatic Speech Recognition". Congratulations, Pau! 🎓 Read all about it: mllp.upv.es/pau-baquero-ea…