معرفی
Himawan Ivan is a researcher affiliated with Queensland University of Technology (QUT), specializing in computer science with a focus on signal processing, speech recognition, and machine learning. His work spans anti-spoofing in speaker verification, deep learning applications in wildlife monitoring (e.g., koala activity detection), and domain adaptation techniques for robust speaker recognition systems. He completed his PhD in 2010 at QUT, titled 'Speech recognition using ad-hoc microphone arrays,' and has contributed to over 28 peer-reviewed publications since 2008.
Research interests include audio processing, neural network architectures for voice biometrics, and perceptual quality optimization in multimedia systems. His collaborations with institutions like the IEEE and ISCA highlight his expertise in interdisciplinary projects, often involving real-world applications such as environmental acoustic analysis and security systems.
Publications between 2016–2019 emphasize advancements in deep neural networks (CNNs, RNNs) for speaker diarization, domain adaptation in PLDA models, and adversarial robustness. Earlier work explored microphone array beamforming and region-of-interest coding in low-bitrate video.
Though no specific grants or awards are listed, his consistent publication record in top venues like INTERSPEECH and IEEE transactions underscore active engagement in academic research.
