Vocapia Research http://www.vocapia.com/ News on Vocapia's recent developments. admin@vocapia.com (Vocapia Admin) en-us Copyright 2006-2013, Vocapia Research 23 Mar 2013 12:10:00 +0200 23 Mar 2013 12:00:00 +0200 1800 Quaero technology day http://www.vocapia.com/news/2013_03_23.html VR130323 Vocapia will participate at the Quaero event in Paris on March 28th. 23 Mar 2013 12:00:00 +0200 Speech-text alignment http://www.vocapia.com/news/2012_12_04.html VR121204 Vocapia Research announces the availability of a speech-text alignment fonctionality on its web service. 4 Dec 2012 12:00:00 +0200 VoxSigma software suite supports Portuguese http://www.vocapia.com/news/2012_10_11.html VR121011 Vocapia Research announces the availability of speech-to-text transcription for the Portuguese language as part of the VoxSigma speech-to-text software suite. 11 Oct 2012 12:00:00 +0200 MediaEval 2012 http://www.vocapia.com/news/2012_06_01.html VR120601 Vocapia Research contributes to MediaEval 2012. 1 Jun 2012 12:00:00 +0200 The Vocapia Research ASR Systems for Evalita 2011 http://www.vocapia.com/publications/evalita_report4.pdf VR120121b This document describes the speech recognizers submitted by Vocapia Research to the Evalita 2011 evaluation for the open un- constrained automatic speech recognition (ASR) task. 21 Jan 2012 12:00:00 +0200 Speech Recognition for Machine Translation in Quaero http://www.vocapia.com/publications/iwslt11_quaeroASR.pdf VR120121a This paper describes the speech-to-text systems used to provide automatic transcriptions used in the Quaero 2010 evaluation of Machine Translation from speech. 21 Jan 2012 10:00:00 +0200 VoxSigma software suite supports Polish and Greek http://www.vocapia.com/news/2012_01_17.html VR120117 Vocapia Research announces the availability of two additional languages, Polish and Greek, in the VoxSigma speech-to-text software suite. 17 Jan 2012 12:00:00 +0200 A Scalable Video Search Engine Based on Audio Content Indexing and Topic Segmentation http://www.vocapia.com/publications/NEMSummit2011_final2.pdf VR111216 This article describes an interface for browsing or searching news broadcasts that exploits these new language processing tools. 16 Dec 2011 10:00:00 +0200 Vocapia results in Evalita http://www.vocapia.com/news/2011_11_02.html VR111102 The high performance of Vocapia Research's speech-to-text technology has once again been demonstrated on the ASR benchmark task of Evalita 2011. 02 Nov 2011 12:00:00 +0200 Comparing Multi-Stage Approaches for Cross-Show Speaker Diarization http://www.vocapia.com/publications/viet-anh-tran_comparing_interspeech11.pdf VR110929 Acoustic speaker diarization is investigated for situations where a collection of shows from the same source needs to be processed. 29 Sep 2011 10:00:00 +0200 Vocapia supports TRECVID 2011 http://www.vocapia.com/news/2011_07_23.html VR110723 Vocapia Research in collaboration with LIMSI-CNRS has provided automatic transcriptions of multilingual audiovideo data for TRECVID 2011. 23 Jul 2011 12:00:00 +0200 Vocapia supports MediaEval 2011 http://www.vocapia.com/news/2011_07_15.html VR110715 Vocapia Research and LIMSI-CNRS have partnered to provide automatic transcriptions of audiovideo data for two MediaEval 2011 tasks. 15 Jul 2011 12:00:00 +0200 Development of a Speech-to-Text Transcription System for Finnish http://www.vocapia.com/publications/sltu10fin.pdf VR101118 This paper describes the development of a speech-to-text transcription system for the Finnish language. 18 Nov 2010 12:00:00 +0200