The MGB-2 challenge: Arabic multi-dialect broadcast media recognition

@article{Ali2016TheMC,
  title={The MGB-2 challenge: Arabic multi-dialect broadcast media recognition},
  author={Ahmed M. Ali and P. Bell and James R. Glass and Yacine Messaoui and Hamdy Mubarak and S. Renals and Yifan Zhang},
  journal={2016 IEEE Spoken Language Technology Workshop (SLT)},
  year={2016},
  pages={279-284}
}
  • Ahmed M. Ali, P. Bell, +4 authors Yifan Zhang
  • Published 2016
  • Computer Science
  • 2016 IEEE Spoken Language Technology Workshop (SLT)
This paper describes the Arabic Multi-Genre Broadcast (MGB-2) Challenge for SLT-2016. Unlike last year's English MGB Challenge, which focused on recognition of diverse TV genres, this year, the challenge has an emphasis on handling the diversity in dialect in Arabic speech. Audio data comes from 19 distinct programmes from the Aljazeera Arabic TV channel between March 2005 and December 2015. Programmes are split into three groups: conversations, interviews, and reports. A total of 1,200 hours… Expand
46 Citations
Speech recognition challenge in the wild: Arabic MGB-3
  • 56
  • PDF
Aalto system for the 2017 Arabic multi-genre broadcast challenge
  • 13
  • PDF
The MGB-5 Challenge: Recognition and Dialect Identification of Dialectal Arabic Speech
  • A. Ali, S. Shon, +5 authors K. Choukri
  • Computer Science
  • 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
  • 2019
  • 13
  • PDF
MIT-QCRI Arabic dialect identification system for the 2017 multi-genre broadcast challenge
  • 15
  • PDF
Automatic speech recognition of Arabic multi-genre broadcast media
  • 11
  • PDF
LIUM ASR systems for the 2016 Multi-Genre Broadcast Arabic challenge
  • 12
  • PDF
JHU Kaldi system for Arabic MGB-3 ASR challenge using diarization, audio-transcript alignment and transfer learning
  • 28
  • Highly Influenced
  • PDF
Development of the MIT ASR system for the 2016 Arabic Multi-genre Broadcast Challenge
  • 9
  • PDF
Multi-Dialect Arabic Speech Recognition
  • Abbas Raza Ali
  • Computer Science
  • 2020 International Joint Conference on Neural Networks (IJCNN)
  • 2020
  • PDF
DARTS: Dialectal Arabic Transcription System
  • 4
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 16 REFERENCES
QCRI advanced transcription system (QATS) for the Arabic Multi-Dialect Broadcast media recognition: MGB-2 challenge
  • 39
  • PDF
LIUM ASR systems for the 2016 Multi-Genre Broadcast Arabic challenge
  • 12
  • PDF
Development of the MIT ASR system for the 2016 Arabic Multi-genre Broadcast Challenge
  • 9
  • PDF
The MGB challenge: Evaluating multi-genre broadcast media recognition
  • P. Bell, M. Gales, +8 authors P. Woodland
  • Computer Science
  • 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)
  • 2015
  • 101
  • PDF
A complete KALDI recipe for building Arabic speech recognition systems
  • 69
  • PDF
The NDSC transcription system for the 2016 multi-genre broadcast challenge
  • 7
  • PDF
Improving the Arabic Pronunciation Dictionary for Phone and Word Recognition with Linguistically-Based Pronunciation Rules
  • 60
  • Highly Influential
  • PDF
Lightly supervised recognition for automatic alignment of large coherent speech recordings
  • 104
  • PDF
The Kaldi Speech Recognition Toolkit
  • 4,478
  • PDF
SRILM - an extensible language modeling toolkit
  • 4,895
  • PDF
...
1
2
...