The PF-STAR project intended to contribute to establish future activities in the field of multisensorial and multilingual communication (interface technologies) on firmer bases by providing technological baselines, comparative evaluations, and assessment of prospects of core technologies, which future research and development efforts can build from. To this end, the project addressed three crucial areas: technologies for speech-to-speech translation, the detection and expressions of emotional states, and core speech technologies for children. For each of them, promising technologies/approaches were selected, further developed and aligned towards common baselines. The results were assessed and evaluated with respect to both their performances and future prospects. To maximise the impact, the duration of the project was limited to 24 months, and the workplan was designed to delivered results in two stages: at mid-project term (month 14), and at the end of the project. This permitted to make relevant results available as soon as possible, and in particular on time for them to be used during the preparatory phase of the first call of FP6. The Lehrstuhl für Informatik 6 was involved in the comparative evaluation and further development of speech translation technologies. The statistical approach was compared to an interlingua based approach. After the evaluation phase, the two approaches were further developed and aligned towards common baselines. PF-STAR was supported by the European Union.
Our pick of the week by @DennisFucci: "Encoding of lexical tone in self-supervised models of spoken language" by @linguisticshen, @Phonologician
@afraalishahi, @AriannaBisazza, and @gchrupala, NAACL 2024.
#Speech #SpokenLanguageModels #ToneEncoding #Interpretability #Phonology
⏳Hurry up! Only 4 days left to apply for a PhD position on “Resource-efficient Foundation Models for Automatic Translation” (A10). Don't miss this opportunity!
📅 Deadline: May 7, 4pm (CEST)
👉Info: https://iecs.unitn.it/education/admission/call-for-application
#PhD #NLProc
Last on our power panel: none other than @HelenaMoniz5 🤩 President of @EAMTee and the International Association of Machine Translation. Currently Chair of the Ethics Committee of the Center for Responsible AI (https://centerforresponsible.ai/) with @Unbabel You don't want to miss this!
Our pick of the week by @beomseok_lee_: "UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions" by @Sid_Arora_18, @emonosuke, @pengyf21, @RoshanSSharma2, @shinjiw_at_cmu, et al., 2024.
#SLU #languageunderstanding #speech