Forensic Automatic Speaker Recognition Based on Likelihood Ratio Using Acoustic-phonetic Features Measured Automatically

• Main Authors: Huapeng Wang (Author), Cuiling Zhang (Author)
• Formato: Livro
• Publicado em: Wolters Kluwer Medknow Publications, 2015-01-01T00:00:00Z.
• Assuntos: article
• Acesso em linha: Connect to this object online.

Forensic speaker recognition is experiencing a remarkable paradigm shift in terms of the evaluation framework and presentation of voice evidence. This paper proposes a new method of forensic automatic speaker recognition using the likelihood ratio framework to quantify the strength of voice evidence...