Proceedings of the 7th International MESAQIN (Measurement of Audio and Video Quality in Networks) Conference, Prague, Czech Republic, May 2008.
Speaker Identification in Low-Rate Coded Speech
Cite This Publication
Andrew A. Catellier and Stephen D. Voran, “Speaker Identification in Low-Rate Coded Speech,” in Proceedings of the 7th International MESAQIN (Measurement of Audio and Video Quality in Networks) Conference Prague, Czech Republic, May 2008..
Andrew A. Catellier and Stephen D. Voran
Abstract: While useful speech communication systems must be intelligible, most systems aim to transmit secondary information, such as attributes of a speaker's voice, as well. This secondary information can allow a listener to identify the speaker and his emotional state. Testing speech communications systems for the delivery of intelligible speech is common, but testing for human perception of the delivery of this secondary information is less common, though some prior work has been done. Building on this prior work, we describe the design, implementation, analysis and results of a new listening experiment that characterizes the listener identification of six different speakers using six different low-rate digital speech communication systems. We display these experimental results along with results from our prior work to quantify listener detection of dramatized speaker urgency and word intelligibility in sentence context for the same six speech communication systems. We conclude that the speaker identification task used in this experiment is about three times more robust to communication system degradations than word intelligibility in sentence context. Slide show presented at ETSI Workshop on Effects of Transmission Performance on Multimedia QoS.
Keywords: speech coding; subjective testing; speaker identification; speech intelligibility
For technical information concerning this report, contact:
Stephen D. Voran
Institute for Telecommunication Sciences
(303) 497-3839
svoran@ntia.gov
Disclaimer: Certain commercial equipment, components, and software may be identified in this report to specify adequately the technical aspects of the reported results. In no case does such identification imply recommendation or endorsement by the National Telecommunications and Information Administration, nor does it imply that the equipment or software identified is necessarily the best available for the particular application or uses.
For questions or information on this or any other NTIA scientific publication, contact the ITS Publications Office at ITSinfo@ntia.gov or 303-497-3572.