Instruction-Following Long
Participants are asked to build a model capable of performing the following tasks (All tasks listed for each track are mandatory):
Automatic Speech Recognition (ASR): the speech is transcribed into the same language;- Speech-to-text Translation (S2TT): the speech is translated into the target language;
- Spoken Question Answering (SQA): textual questions have to be answered based on the spoken content in the same language and in a language different from the speech (questions and answers are always in the same language);
- Speech-to-text Summarization (S2TSUM): a summary has to be provided from the spoken content in the same language and in a language different from the speech.
We release the source audio and the instructions, and participants submit their outputs. The instructions can be modified by participants to match their system’s prompts. In SQA, questions are provided both in the same language of the speech (English) and in different languages (German, Italian, Chinese) but they always have to be replied to in the same language of the questions (e.g., an Italian question should be replied to in Italian). Questions can also be nonanswerable, in this case, only the answer “Not answerable.” (and the corresponding Italian “Non è possibile rispondere.”, German “Nicht zu beantworten.”, and Chinese “无法回答。” translations) will be considered correct.
The Long Track will process audio files in WAV format that are, on average, 5–6 minutes long. We provide an example for the Long track, downloadable here. Participants are also allowed to use it as 1-shot example for their model. We also provide useful scripts for parsing inputs and outputs, downloadable here.
IWSLT25INSTRUCT test set
The IWSLT25Instruct test set consists of audio recordings from the scientific domain, specifically presentations of research papers at major NLP conferences within the *ACL community. These recordings feature one of the authors presenting their paper’s scientific content in English.
Entries for Instruction-Following Long
| Language | en |
|---|---|
| de | |
| en | |
| it | |
| zh |