Classification of vocal intensity category from speech using the wav2vec2 and whisper embeddings

M Kodali, S Kadiri, P Alku - Interspeech, 2023 - research.aalto.fi
In speech communication, talkers regulate vocal intensity resulting in speech signals of
different intensity categories (eg, soft, loud). Intensity category carries important information …

[HTML][HTML] AVID: A speech database for machine learning studies on vocal intensity

P Alku, M Kodali, L Laaksonen, SR Kadiri - Speech Communication, 2024 - Elsevier
Vocal intensity, which is quantified typically with the sound pressure level (SPL), is a key
feature of speech. To measure SPL from speech recordings, a standard calibration tone …

Classification of Vocal Intensity Category from Multi-sensor Recordings of Speech

J Ylä-Jääski - 2023 - aaltodoc.aalto.fi
Vocal intensity is a crucial characteristic of speech. The intensity is regulated in the
expression of emotions and with the purpose to propagate speech over longer distances …