While successful on broadcast news, meetings or telephone conversation, state-of-the-art
speaker diarization techniques tend to perform poorly on TV series or movies. In this paper …

While huge progress has been made in machine translation (MT) in recent years, the
majority of MT systems still rely on the assumption that sentences can be translated in …

Understanding the interactive structure of dialogues, such as turn taking behaviour and
change of speakers, is a critical prerequisite for dialogue systems which aim to understand …

Multi-view learning algorithms are powerful representation learning tools, often exploited in
the context of multimodal problems. However, for problems requiring inference at the token …

Though radio and TV broadcast are highly structured documents, state-of-the-art speaker
identification algorithms do not take advantage of this information to improve prediction …

In the existing person identification solutions, multi-modal learning is able to gain a plausible
person identification accuracy in TV Content since supervised information is applied to train …