Overview
My current research focuses on using deep learning to capture head-related transfer functions and, more generally, spatial acoustics and immersive audio. Other research interests include speaker diarization and statistical signal processing for audio applications. More information about my current research can be found at: www.aidanhogg.uk.
Selected Publications
- A. Hogg and L. Picinali: HRTF upsampling: A machine learning approach. In: Basic Auditory Science (BAS), 2023.
- A. Hogg, M. Jenkins, H. Liu, and L. Picinali: Exploring the impact of transfer learning on GAN-based HRTF upsampling. In: Proc. EAA Forum Acusticum, Eur. Congress on Acoust., 2023.
- A. Hogg, M. Jenkins, H. Liu, I. Squires, S. J. Cooper, and L. Picinali: HRTF upsampling with a generative adversarial network using a gnomonic equiangular projection. In: IEEE/ACM Trans. Audio, Speech, Language Process. (TASLP), 2023 (submitted).
- I. Engel, R. Daugintis, T. Vicente, A. Hogg, J. Pauwels, A. Tournier, and L. Picinali: The SONICOM HRTF dataset. J. Audio Eng. Soc. (AES), 2022
- S. McKnight, A. Hogg, V. Neo, and P. Naylor: Studying humanbased speaker diarization and comparing to state-of-the-art systems. In: Proc. Asia-Pacific Signal and Inform. Process. Assoc. Annual Summit and Conf. (APSIPA ASC), 2022.
- V. Neo, S. Weiss, S. McKnight, A. Hogg and P. Naylor: Polynomial eigenvalue decomposition-based target speaker voice activity detection in the presence of competing talkers. In: Proc. Int. Workshop on Acoust. Signal Enhancement (IWAENC), 2022.
- A. Hogg: ‘Did the speaker change?’: Temporal tracking for overlapping speaker segmentation in multi-speaker scenarios. PhD Thesis - Imperial College London, 2022
- S. McKnight, A. Hogg, V. Neo and P. Naylor: A study of salient modulation domain features for speaker identification. In: Proc. AsiaPacific Signal and Inform. Process. Assoc. Annual Summit and Conf. (APSIPA ASC), 2021.
- A. Hogg, V. Neo, S Weiss, C. Evers and P. Naylor: A polynomial eigenvalue decomposition MUSIC approach for broadband sound source localization. In: Proc. IEEE Workshop on Appl. of Signal Process. to Audio and Acoust. (WASPAA), 2021.
- A. Hogg, C. Evers, A. Moore and P. Naylor: Overlapping speaker segmentation using multiple hypothesis tracking of fundamental frequency. In: IEEE/ACM Trans. Audio, Speech, Language Process. (TASLP), 2021.
- A. Hogg, C. Evers and P. Naylor: Multichannel overlapping speaker segmentation using multiple hypothesis tracking of acoustic and spatial features. In: Proc. IEEE Intl. Conf. on Acoust., Speech and Signal Process. (ICASSP), 2021.
- S. McKnight, A. Hogg and P. Naylor: Analysis of phonetic dependence of segmentation errors in speaker diarization. In: Proc. European Signal Process. Conf. (EUSIPCO), 2020.
- A. Hogg, C. Evers and P. Naylor: Multiple hypothesis tracking for overlapping speaker segmentation. In: Proc. IEEE Workshop on Appl. of Signal Process. to Audio and Acoust. (WASPAA), 2019.
- D. Sharma, A. Hogg, Y. Wang, A. Nour-Eldin and P. Naylor: Non-intrusive POLQA estimation of speech quality using recurrent neural networks. In: Proc. European Signal Process. Conf. (EUSIPCO), 2019.
- A. Hogg, C. Evers and P. Naylor: Speaker change detection using fundamental frequency with application to multi-talker segmentation. In: Proc. IEEE Intl. Conf. on Acoust., Speech and Signal Process. (ICASSP), 2019.