Exploiting Convolutional Neural Networks for Phonotactic Based Dialect Identification

Najafian, Maryam; Khurana, Sameer; Shan, Suwon; Ali, Ahmed; Glass, James

doi:10.1109/icassp.2018.8461486

Cited by 30 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Khurana et al [5] 67 73 Shon et al [9] 69.97 75.00 Najafian et al [7] 59.72 73.27 Bulut et al [10] -79.76 Our approach 73.39 81.36 Table 9: Performance comparison to previous works on same MGB-3 dataset pared to previous studies. Table 9 shows summary performance of previous studies on same MGB-3 Arabic dialect dataset.…”

Section: Systems Accuracy(%) Single System Fusion Systemmentioning

confidence: 89%

“…A DID benchmark of the task was attained using the i-vector framework using bottleneck features [4]. Using linguistic features such as words and characters results in similar performance to that obtained via acoustic features with a Convolutional Neural Network (CNN)based backend [5,6,7]. Since the linguistic feature space is different from the acoustic feature space, a fusion of the results from both feature representations has been shown to be beneficial [6,5,8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Neural Network and Language Embeddings for End-to-End Dialect Recognition

Shon¹,

Ali²,

Glass³

2018

The Speaker and Language Recognition Workshop (Odyssey 2018)

Self Cite

View full text Add to dashboard Cite

Dialect identification (DID) is a special case of general language identification (LID), but a more challenging problem due to the linguistic similarity between dialects. In this paper, we propose an end-to-end DID system and a Siamese neural network to extract language embeddings. We use both acoustic and linguistic features for the DID task on the Arabic dialectal speech dataset: Multi-Genre Broadcast 3 (MGB-3). The endto-end DID system was trained using three kinds of acoustic features: Mel-Frequency Cepstral Coefficients (MFCCs), log Mel-scale Filter Bank energies (FBANK) and spectrogram energies. We also investigated a dataset augmentation approach to achieve robust performance with limited data resources. Our linguistic feature research focused on learning similarities and dissimilarities between dialects using the Siamese network, so that we can reduce feature dimensionality as well as improve DID performance. The best system using a single feature set achieves 73% accuracy, while a fusion system using multiple features yields 78% on the MGB-3 dialect test set consisting of 5 dialects. The experimental results indicate that FBANK features achieve slightly better results than MFCCs. Dataset augmentation via speed perturbation appears to add significant robustness to the system. Although the Siamese network with language embeddings did not achieve as good a result as the endto-end DID system, the two approaches had good synergy when combined together in a fused system. 1

show abstract

Section: Systems Accuracy(%) Single System Fusion Systemmentioning

confidence: 89%

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Network and Language Embeddings for End-to-End Dialect Recognition

Shon¹,

Ali²,

Glass³

2018

The Speaker and Language Recognition Workshop (Odyssey 2018)

Self Cite

View full text Add to dashboard Cite

show abstract

“…DNN consisting of multiple interconnected layers between the input and output layers were used in speech recognition tasks (Najafian et al 2018). DNNs had not been used just as classifiers but they were also used as feature extractors (Ali et al 2015).…”

Section: Bottleneck Featuresmentioning

confidence: 99%

Spoken Arabic dialect recognition using X-vectors

Hanani

Naser

2020

Nat. Lang. Eng.

View full text Add to dashboard Cite

This paper describes our automatic dialect identification system for recognizing four major Arabic dialects, as well as Modern Standard Arabic. We adapted the X-vector framework, which was originally developed for speaker recognition, to the task of Arabic dialect identification (ADI). The training and development ADI VarDial 2018 and VarDial 2017 were used to train and test all of our ADI systems. In addition to the introduced X-vectors, other systems use the traditional i-vectors, bottleneck features, phonetic features, words transcriptions, and GMM-tokens. X-vectors achieved good performance (0.687) on the ADI 2018 Discriminating between Similar Languages shared task testing dataset, outperforming other systems. The performance of the X-vector system is slightly improved (0.697) when fused with i-vectors, bottleneck features, and word uni-gram features.

show abstract

“…The fine-grained Arabic Dialect Identification (ADI) task involved dialect identification of speech from YouTube across 17 dialects. The previous MGB-3 challenge resulted in studies covering diverse dialect identification topics such as domain adaptation [4,5], semi-supervised learning [6,7,8,9], and linguistic feature extraction [10,11]. However MGB-3 was limited to 5 dialects.…”

Section: Introductionmentioning

confidence: 99%

The MGB-5 Challenge: Recognition and Dialect Identification of Dialectal Arabic Speech

Ali

Shon²,

Samih

et al. 2019

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

Self Cite

View full text Add to dashboard Cite

This paper describes the fifth edition of the Multi-Genre Broadcast Challenge (MGB-5), an evaluation focused on Arabic speech recognition and dialect identification. MGB-5 extends the previous MGB-3 challenge in two ways: first it focuses on Moroccan Arabic speech recognition; second the granularity of the Arabic dialect identification task is increased from 5 dialect classes to 17, by collecting data from 17 Arabic speaking countries. Both tasks use YouTube recordings to provide a multi-genre multi-dialectal challenge in the wild. Moroccan speech transcription used about 13 hours of transcribed speech data, split across training, development, and test sets, covering 7-genres: comedy, cooking, family/kids, fashion, drama, sports, and science (TEDx). The fine-grained Arabic dialect identification data was collected from known YouTube channels from 17 Arabic countries. 3,000 hours of this data was released for training, and 57 hours for development and testing. The dialect identification data was divided into three sub-categories based on the segment duration: short (under 5 s), medium (5-20 s), and long (>20 s). Overall, 25 teams registered for the challenge, and 9 teams submitted systems for the two tasks. We outline the approaches adopted in each system and summarize the evaluation results.

show abstract

Exploiting Convolutional Neural Networks for Phonotactic Based Dialect Identification

Cited by 30 publications

References 23 publications

Convolutional Neural Network and Language Embeddings for End-to-End Dialect Recognition

Convolutional Neural Network and Language Embeddings for End-to-End Dialect Recognition

Spoken Arabic dialect recognition using X-vectors

The MGB-5 Challenge: Recognition and Dialect Identification of Dialectal Arabic Speech

Contact Info

Product

Resources

About