Experiments of GMM based speaker identification
2011 (English)In: URAI 2011: 2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence, 2011, 26-31 p.Conference paper (Refereed)
In human-robot interaction areas, the robot is often expected to recognize the identity of the speaker in some specific scenarios. It is a kind of biometric modality, and in general using statistical model is a classical and powerful method dealing with speaker identification problem. In this paper, we apply the Gaussian mixture model (GMM) on the speech feature distribution modeling and build the speaker identification system under MATLAB platform. Experiments are conducted on practical speech database and we also further give some insights into feature extraction, different length input utterances analysis and the impostor situation.
Place, publisher, year, edition, pages
2011. 26-31 p.
, URAI 2011 - 2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence
Feature Extraction, Gaussian Mixture Model (GMM), Speaker Identification (SI), Speech Signal Processing, Gaussian Mixture Model, Interaction area, MATLAB platform, Speaker identification, Speaker identification systems, Speech database, Speech features, Statistical models, Artificial intelligence, Biometrics, Experiments, Robots, Signal processing, Speech recognition, Loudspeakers
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-149778DOI: 10.1109/URAI.2011.6145927ScopusID: 2-s2.0-84863150316ISBN: 9781457707223OAI: oai:DiVA.org:kth-149778DiVA: diva2:742021
2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2011; Incheon, South Korea, 23-26 November, 2011
QC 201408292014-08-292014-08-272014-10-03Bibliographically approved