Researchers use RL-based neural architecture search to find compact audio-visual speech enhancement models for edge devices, cutting parameters from 22M to 2.9M while maintaining strong performance.

#AudioVisualAI #NeuralArchitectureSearch #EdgeAI #SpeechProcessing
https://arxiv.org/abs/2610.12796

Delighted to share our paper in Springer’s MTAP:

“APEDM: a new voice casting system using acoustic–phonetic encoder-decoder mapping” 🎙️🧠

Introducing a novel non-linear mapping framework for cross-lingual dubbing (EN ➡️ FA) using E2PCast.

🔗 link.springer.com/article/10.1...

#SpeechProcessing

Excited to share our paper in Springer’s SIVP:

“E2PCast: an English to Persian voice casting dataset” 🎙️🎬

Introducing the first dataset for cross-lingual dubbing & voice casting (EN ➡️ FA) with benchmark evaluations.

🔗 link.springer.com/article/10.1...

#SpeechProcessing #VoiceCasting #AudioAI

🎙️ Does knowing a speaker’s gender actually boost speaker recognition?

In our latest paper in Soft Computing (Springer), we explore gender effects via bio-inspired filterbanks (Gammatone, Cascade, etc.)

🔗 link.springer.com/article/10.1...

#SpeechProcessing #AudioAI #AudioDeepFake #ISPlab