Speech emotion recognition based on Arabic features

Meddeb, Mohamed; Karray, Hichem; Alimi, Adel M.

doi:10.1109/isda.2015.7489165

Cited by 15 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some Arabic speeches emotion datasets have been proposed in the literature, see [1]- [3], [5], [19]. Each dataset has a different set of classes or labels, for example, the Arabic audio acted dataset proposed in [20] has five labels (Happiness, Sadness, Neutral, Anger, Fear), and the dataset proposed in [15] has three classes (Happy, Surprised, and Angry), while the dataset proposed in [19] has labels (Happy, Sad, Neutral, Angry, Surprise, Disgust).…”

Section: Arabic Baved Datasetmentioning

confidence: 99%

Arabic Speech Emotion Recognition Employing Wav2vec2.0 and HuBERT Based on BAVED Dataset

Mohamed,

Aly

2021

Preprint

View full text Add to dashboard Cite

Recently, there have been tremendous research outcomes in the fields of speech recognition and natural language processing. This is due to the well-developed multilayers deep learning paradigms such as wav2vec2.0, Wav2vecU, WavBERT, and HuBERT that provide better representation learning and high information capturing. Such paradigms run on hundreds of unlabeled data, then fine-tuned on a small dataset for specific tasks. This paper introduces a deep learning constructed emotional recognition model for Arabic speech dialogues. The developed model employs the state of the art audio representations include wav2vec2.0 and HuBERT. The experiment and performance results of our model overcome the previous known outcomes.

show abstract

Section: Arabic Baved Datasetmentioning

confidence: 99%

Arabic Speech Emotion Recognition Employing Wav2vec2.0 and HuBERT Based on BAVED Dataset

Mohamed,

Aly

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Natural Arabic speech database is built, and this database comprises three emotions: happiness, angry and surprise [33]. Tunisian actors were employed to build Tunisian dialect database which contains five emotions: happy, anger, fear, sadness and neutral emotions [34]. There are other databases have been built in Arabic language, emotional database (MEDB) in Moroccan [35], Emirati speech database (ESD) [36] and Egyptian Arabic speech emotion (EYASE) [37].…”

Section: Related Workmentioning

confidence: 99%

Recognition of emotions in the Algerian Dialect Speech

Horkous¹,

Guerti²

2021

IJCDS

View full text Add to dashboard Cite

“…Tunisian emotional database was built by professional Tunisian actors. This database contains five types of emotions including happy, anger, sadness, fear and neutral [37]. Moroccan emotional database (MEDB) was created from broadcasts on the YouTube channel [38].…”

Section: Related Workmentioning

confidence: 99%

“…From results, it has been concluded that the performance of classifier depends on the type of database [49]. A hybrid classifier (GMM-DNN) in [36] gave better performance when compared with SVM and MLP (multilayer perception) classifiers [37]. The performance of KNN classifier has been compared with SVM classifier.…”

Section: Related Workmentioning

confidence: 99%