Actions
  • shareshare
  • link
  • cite
  • add
add
auto_awesome_motion View all 6 versions
Publication . Preprint . Conference object . Contribution for newspaper or weekly magazine . Article . 2017

Speech Recognition Challenge in the Wild: Arabic MGB-3

Ahmed Ali; Stephan Vogel; Steve Renals;
Open Access
English
Published: 01 Jan 2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Country: United Kingdom
Abstract
This paper describes the Arabic MGB-3 Challenge - Arabic Speech Recognition in the Wild. Unlike last year's Arabic MGB-2 Challenge, for which the recognition task was based on more than 1,200 hours broadcast TV news recordings from Aljazeera Arabic TV programs, MGB-3 emphasises dialectal Arabic using a multi-genre collection of Egyptian YouTube videos. Seven genres were used for the data collection: comedy, cooking, family/kids, fashion, drama, sports, and science (TEDx). A total of 16 hours of videos, split evenly across the different genres, were divided into adaptation, development and evaluation data sets. The Arabic MGB-Challenge comprised two tasks: A) Speech transcription, evaluated on the MGB-3 test set, along with the 10 hour MGB-2 test set to report progress on the MGB-2 evaluation; B) Arabic dialect identification, introduced this year in order to distinguish between four major Arabic dialects - Egyptian, Levantine, North African, Gulf, as well as Modern Standard Arabic. Two hours of audio per dialect were released for development and a further two hours were used for evaluation. For dialect identification, both lexical features and i-vector bottleneck features were shared with participants in addition to the raw audio recordings. Overall, thirteen teams submitted ten systems to the challenge. We outline the approaches adopted in each system, and summarise the evaluation results.
Subjects by Vocabulary

Microsoft Academic Graph classification: History Arabic language.human_language language Arabic speech recognition Drama Linguistics Comedy Raw audio format Modern Standard Arabic Identification (information) Broadcast television systems

Subjects

Computation and Language (cs.CL), FOS: Computer and information sciences, Computer Science - Computation and Language

20 references, page 1 of 2

[1] P. Bell, M. JF Gales, T. Hain, J. Kilgour, P. Lanchantin, X. Liu, A. McParland, S. Renals, O. Saz, M. Wester, and P. Woodland, “The MGB challenge: Evaluating multigenre broadcast media recognition,” in ASRU, 2015.

[2] A. Ali, P. Bell, J. Glass, Y. Messaoui, H. Mubarak, S. Renals, and Y. Zhang, “The MGB-2 Challenge: Arabic multi-dialect broadcast media recognition,” in SLT, 2016.

[3] A. Ali, P. Nakov, P. Bell, and S. Renals, “WERd: Using social text spelling variants for evaluating dialectal speech recognition,” in ASRU, 2017.

[4] A. Ali, W. Magdy, P. Bell, and S. Renals, “Multireference WER for evaluating ASR for languages with no orthographic rules,” in ASRU, 2015.

[5] S. Malmasi, M. Zampieri, N. Ljubesˇic, P. Nakov, A. Ali, and Jo¨rg Tiedemann, “Discriminating between similar languages and Arabic dialect identification: A report on the third DSL shared task,” VarDial 3, p. 1, 2016.

[6] M. Zampieri, S. Malmasi, N. Ljubesˇic, P. Nakov, A. Ali, J. Tiedemann, Y. Scherrer, and N. Aepli, “Findings of the VarDial evaluation campaign 2017,” VarDial 2017, p. 1, 2017. [OpenAIRE]

[7] S. Khurana and A. Ali, “QCRI Advanced Transcription System (QATS) for the Arabic multi-dialect broadcast media recognition: MGB-2 Challenge,” in SLT, 2016.

[8] A. Ali, N. Dehak, P. Cardinal, S. Khurana, S. Harsha Yella, J. Glass, P. Bell, and S. Renals, “Automatic dialect detection in Arabic broadcast speech,” in Interspeech, 2016. [OpenAIRE]

[9] S. Wray and A. Ali, “Crowdsource a little to label a lot: Labeling a speech corpus of Dialectal Arabic,” in Interspeech, 2015.

[10] A. Ali, Y. Zhang, and S. Vogel, “QCRI advanced transcription system (QATS),” in SLT, 2014.

Funded by
EC| SUMMA
Project
SUMMA
Scalable Understanding of Multilingual Media
  • Funder: European Commission (EC)
  • Project Code: 688139
  • Funding stream: H2020 | RIA
Validated by funder
Related to Research communities
Digital Humanities and Cultural Heritage
moresidebar