{"ID":5675361,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-07T01:06:03.009715918Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.02129","arxiv_id":"2607.02129","title":"Speaker head orientation estimation with a single microphone array using phase spectrogram features","abstract":"Estimating a speaker's head orientation from audio can provide valuable information in smart environments, meetings, and driver monitoring. We propose a novel approach that leverages the phase component of the short-time Fourier transform from a single microphone array as input to a deep neural network combining convolutional, recurrent, and self-attention layers. Unlike prior methods that use physics-informed handcrafted features or raw waveform inputs, our approach enables robust learning from simulated and real data. Trained on a large-scale dataset generated with voice directivity patterns and fine-tuned on real recordings, our model achieves state-of-the-art accuracy, outperforming baselines under both clean and noisy conditions. Personalization experiments further demonstrate significant gains, reaching a mean angular error of 11.3 degrees when adapting to individual users and environments.","short_abstract":"Estimating a speaker's head orientation from audio can provide valuable information in smart environments, meetings, and driver monitoring. We propose a novel approach that leverages the phase component of the short-time Fourier transform from a single microphone array as input to a deep neural network combining convol...","url_abs":"https://arxiv.org/abs/2607.02129","url_pdf":"https://arxiv.org/pdf/2607.02129v1","authors":"[\"Balint Turi\",\"Archontis Politis\",\"Parthasaarathy Sudarsanam\",\"Tuomas Virtanen\"]","published":"2026-07-02T13:05:36Z","proceeding":"cs.SD","tasks":"[\"cs.SD\"]","methods":"[]","has_code":false}