Approaches from standard automatic speaker recognition, which rely on cepstral features, suffer the problem of lack of interpretability for forensic applications. But the growing practice of using "higher-level" features in automatic systems offers promise in this regard. We provide an overview of automatic higher-level systems and discuss potential advantages, as well as issues, for their use in the forensic context.
Bibliographic reference. Shriberg, Elizabeth / Stolcke, Andreas (2008): "The case for automatic higher-level features in forensic speaker recognition", In INTERSPEECH-2008, 1509-1512.