3 papers
eess.AS2026
HyWA: Architecture-Preserving Personalized Voice Activity Detection for Full-Duplex Voice Assistants
Mahsa Ghazvini Nejad, Hamed Jafarzadeh Asl, Amin Edraki +4
Voice activity detection (VAD) serves as an early gate in voice-assistant pipelines for smart devices. Because conventional VADs respond to speech from any speaker, nearby conversa…
cs.LG2025
MoKA: Mixture of Kronecker Adapters
Mohammadreza Sadeghi, Mahsa Ghazvini Nejad, MirHamed Jafarzadeh Asl +4
Parameter-efficient fine-tuning (PEFT) is essential for reducing the computational overhead of large language models (LLMs). Low-rank family adapters are commonly used to control t…
eess.AS2025
Tiny Noise-Robust Voice Activity Detector for Voice Assistants
Hamed Jafarzadeh Asl, Mahsa Ghazvini Nejad, Amin Edraki +2
Voice Activity Detection (VAD) in the presence of background noise remains a challenging problem in speech processing. Accurate VAD is essential in automatic speech recognition, vo…