Edinburgh Research Explorer

Speech Recognition Challenge in the Wild: Arabic MGB-3

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8268952
Original languageEnglish
Title of host publicationIEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2017)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages316-322
Number of pages7
ISBN (Electronic)978-1-5090-4788-8
ISBN (Print)978-1-5090-4789-5
DOIs
Publication statusPublished - 25 Jan 2018
Event2017 IEEE Automatic Speech Recognition and Understanding Workshop - Okinawa, Japan
Duration: 16 Dec 201720 Dec 2017
https://asru2017.org/

Conference

Conference2017 IEEE Automatic Speech Recognition and Understanding Workshop
Abbreviated titleASRU 2017
CountryJapan
CityOkinawa
Period16/12/1720/12/17
Internet address

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.

Event

2017 IEEE Automatic Speech Recognition and Understanding Workshop

16/12/1720/12/17

Okinawa, Japan

Event: Conference

Download statistics

No data available

ID: 43692043