The paper deals with training of speaker-clustered acoustic models. Various training techniques Maximum Likelihood, Discriminative Training and two adaptation based on the MAP and Discriminative MAP were tested in order to minimize an impact of speaker changes to the correct function of the recognizer when a response of the automatic cluster detector is delayed or incorrect. Such situation is v...

Despite the central place occupied by language transfer of audiovisual products, particularly in the European cinema and television sector, audience perception of both dubbing and subtitling is a largely neglected field of study and research. When, however, we start looking into the available research on the perception of translated humor and, more specifically, of the perception of humor as re...

Reception studies have become an essential element in the audiovisual translation research. In fact, transnational turn study of media audiences has led to a reciprocity between reception and This aims at conducting semiotic analysis Arab viewers’ Arabic subtitling Netflix’s Swedish series

This paper describes the move to a multithreaded implementation of a Recursive Transition Network Viterbi speech decoder, undertaken with the objective of performing low-latency synchronous decoding on live audio streams to support online subtitling. The approach was meant to be independent on any specific hardware, in order to be easily exploitable on common computers, and portable to differen...

In this paper, we present our initial efforts in the task of Automatically Synchronizing live spoken Utterances with their Transcripts (textual contents) (ASUT). We address the problem of online detecting of the end time of a spoken utterance given its textual content, which is one of the key problems of the ASUT task. A frame-synchronous likelihood ratio test (FS-LRT) procedure is proposed and...

Data-driven approaches to sentence compression define the task as dropping any subset of words from the input sentence while retaining important information and grammaticality. We show that only 16% of the observed compressed sentences in the domain of subtitling can be accounted for in this way. We argue that part of this is due to evaluation issues and estimate that a deletion model is in fac...