Heterogeneous Reservoir Computing Models for Persian Speech Recognition

Ansari, Zohreh; Farzin, Pourhoseini,; Hadaeghi, Fatemeh

doi:10.1109/ijcnn55064.2022.9892570

Cited by 3 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We investigate our setup using the spoken digits recognition task, already used in prior works on RC [16]- [19]. We experimentally validate analogous results obtained by previous numerical studies on DRC for speech recognition [8], [20], and we further investigate the response of the system when environmental noise is present in the input recordings. Our results confirm the superiority of DRC with respect to shallow RC architectures.…”

Section: Introductionsupporting

confidence: 64%

“…We experimentally validated previous analogous numerical results of Deep Reservoir Computing on the speech recognition task [8], [20], investigating further to check whether the presence of environmental noise can be detrimental to the performance. Our results clearly show that a Deep Reservoir Computer outperforms a "shallow" Reservoir Computer, when considering networks of same size.…”

Section: Discussionmentioning

confidence: 60%

See 1 more Smart Citation

Real-Time Photonic Deep Reservoir Computing for Speech Recognition

Picco,

Massar

2023

2023 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Reservoir Computing is a bio-inspired computing paradigm with the main advantage of being less computationally demanding than state-of-the-art neural networks. However, the performance of reservoir computing is limited comparing to other power-hungry Machine Learning algorithms. Deep Reservoir Computing addresses this problem by using multiple interconnected reservoirs to provide greater capacity for processing information, leading to improved performance. In this work we propose a photonic Deep Reservoir Computer: we test it on the speech recognition task, and we experimentally confirm its effectiveness. We show how some design choices can simplify the realization of a Reservoir Computer. Our photonic system is the first experimental Deep Reservoir Computer that can process speech recordings in real-time. We thus hope that this work can pave the way for efficient dedicated hardware for high-speed signal processing.

show abstract