NESPOLE! System has been developed using two scenarios: the tourism scenario and the first aid medical assistance scenario. During the project life three main data collection have been carried on in order to develop the first and the second showcase. During the first year 191 dialogues have been collected. There are 62 German dialogues recorded, 61 Italian, 37 English and 31 French. Particularly an amount of 6 hours of dialogues for Italian and French, 7 hours for English, 8 hours for German has been recorded. Dialogues were about five predefined tourism scenarios. During the last year two major data collections have been carried on: the first one aimed at expanding the tourism scenario and the second one at addressing the medical domain. For the monolingual data collection five tourism scenarios were developed; 66 dialogues were recorded yielding 994.57 minutes of data: 243.52 minutes comprised in sixteen English dialogues, 246 minutes in sixteen German dialogues, 272.52 minutes in seventeen French dialogues and 232.53 minutes in seventeen Italian dialogues. The data collection on the medical domain involved Italian, English and German languages. A total of 49 dialogues were collected. The recording results in a total of 8 hours 25 minutes of audio files.
Our pick of the week by @mgaido91: "AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM" by @RuchaoFan, Bo Ren, Yuxuan Hu, Rui Zhao, Shujie Liu, Jinyu Li (2024).
#NLProc #Speech #instructionfollowing #zeroshot #speechtech #speechllm
AI is transforming cultural heritage, but what have we learned?
Come and join the #AI4Culture movement at our Final Conference on March 10 in Hilversum to explore AI’s current & future impact on cultural heritage.
Details & Registration: https://pretix.eu/EFHA/AI4Culture/
@EU_HaDEA
BOUQuET💐: an OPEN INITIATIVE aimed at building an evaluation dataset for massively multilingual text-to-text MT.
Let’s make MT available for any written language!
We are inviting everyone to contribute: ➡️
More details at: https://arxiv.org/abs/2502.04314
I am happy to announce that I will speak about our recent work "How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?" at the SlatorCon in March 🎊
📃 Preprint available here: