The article “Direct Segmentation Models for Streaming Speech Translation”, by Javier Iranzo and other MLLP researchers, has been accepted for publication at the ACL’s EMNLP 2020 conference (CORE A).
The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), organized by the Association for Computer Linguistics (ACL) and to be held this year online on November 16–20, is one of the world’s largest technical conferences on natural language processing, with a CORE A conference ranking.
We’re proud to announce that the MLLP article “Direct Segmentation Models for Streaming Speech Translation”, by MLLP researchers Javier Iranzo-Sánchez, Adrià Giménez Pastor, Joan Albert Silvestre-Cerdà, Pau Baquero-Arnal, Jorge Civera Saiz and Alfons Juan, has been accepted for publication at the conference. You can read here the paper’s abstract:
The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) system. These systems are usually connected by a segmenter that splits the ASR output into, hopefully, semantically self-contained chunks to be fed into the MT system. This is especially challenging in the case of streaming ST, where latency requirements must also be taken into account. This work proposes novel segmentation models for streaming ST that incorporate not only textual, but also acoustic information to decide when the ASR output is split into a chunk. An extensive and thorough experimental setup is carried out on the Europarl-ST dataset to prove the contribution of acoustic information to the performance of the segmentation model in terms of BLEU score in a streaming ST scenario. Finally, comparative results with previous work also show the superiority of the segmentation models proposed in this work.
Since the foundation of the MLLP research group (2014), MLLP members have published over 10 international journal articles (IEEE-ACM Trans. Audio Speech Lang., 2018; Pattern Recognition Letters, 51, 2015; …) and over 20 international conference papers (Interspeech 2020; ICASSP 2020 [1][2]; Interspeech 2019; AMTA 2014; …). You can browse through all of the 200+ publications by MLLP researchers in the Publications section in our website.
We at the MLLP are very glad to participate in EMNLP 2020. We look forward to seeing you there!