Similarity Search of Acted Voices for Automatic Voice Casting - Sorbonne Université Access content directly
Journal Articles IEEE/ACM Transactions on Audio, Speech and Language Processing Year : 2016

Similarity Search of Acted Voices for Automatic Voice Casting

Nicolas Obin
Axel Roebel

Abstract

This paper presents a large-scale similarity search of professionally acted voices for computer-aided voice casting. The proposed voice casting system explores Gaussian mixture model-based acoustic models and multilabel recognition of perceived paralinguistic content (speaker states and speaker traits, e.g., age/gender, voice quality, emotion) for the voice casting of professionally acted voices. First, acoustic models (universal background model, super-vector, i-vector) are constructed to model the acoustic space of voices, from which the similarity between voices can be measured directly in the acoustic space. Second, multiple binary classification of speaker traits and states is added to the acoustic models in order to represent the vocal signature of a voice, which is then used to measure the similarity between voices in the paralinguistic space. Finally, a similarity search is processed in order to determine the set of target actors that are the most similar to the voice of a source actor. In a subjective experiment conducted in the real-context of cross-language voice casting, the multilabel scoring system significantly outperforms the acoustic scoring system. This constitutes a proof of concept for the role of perceived para-linguistic categories in the perception of voice similarity.
Fichier principal
Vignette du fichier
taslp-obin-2580302-proof.pdf (598.18 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01464715 , version 1 (10-02-2017)

Identifiers

Cite

Nicolas Obin, Axel Roebel. Similarity Search of Acted Voices for Automatic Voice Casting. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2016, 24 (9), pp.1642 - 1651. ⟨10.1109/TASLP.2016.2580302⟩. ⟨hal-01464715⟩
434 View
444 Download

Altmetric

Share

Gmail Facebook X LinkedIn More