Amirhossein Hajavi

According to our database, Amirhossein Hajavi authored at least 10 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2024

Audio Representation Learning by Distilling Video as Privileged Information.

Amirhossein Hajavi, Ali Etemad

IEEE Trans. Artif. Intell., January, 2024

2023

Fine-Grained Early Frequency Attention for Deep Speaker Representation Learning.

Amirhossein Hajavi, Ali Etemad

IEEE Trans. Artif. Intell., December, 2023

A Study on Bias and Fairness in Deep Speaker Recognition.

Amirhossein Hajavi, Ali Etemad

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Fine-grained Early Frequency Attention for Deep Speaker Recognition.

Amirhossein Hajavi, Ali Etemad

Proceedings of the International Joint Conference on Neural Networks, 2022

2021

FluentNet: End-to-End Detection of Stuttered Speech Disfluencies With Deep Learning.

Tedd Kourkounakis, Amirhossein Hajavi, Ali Etemad

IEEE ACM Trans. Audio Speech Lang. Process., 2021

Siamese Capsule Network for End-to-End Speaker Recognition in the Wild.

Amirhossein Hajavi, Ali Etemad

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

FluentNet: End-to-End Detection of Speech Disfluency with Deep Learning.

Tedd Kourkounakis, Amirhossein Hajavi, Ali Etemad

CoRR, 2020

Knowing What to Listen to: Early Attention for Deep Speech Representation Learning.

Amirhossein Hajavi, Ali Etemad

CoRR, 2020

Detecting Multiple Speech Disfluencies Using a Deep Residual Network with Bidirectional Long Short-Term Memory.

Tedd Kourkounakis, Amirhossein Hajavi, Ali Etemad

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

A Deep Neural Network for Short-Segment Speaker Recognition.

Amirhossein Hajavi, Ali Etemad

Proceedings of the Interspeech 2019, 2019