Transmitting voice communication over untrusted networks puts personal information at risk. Although voice streams are typically encrypted to prevent unwanted eavesdropping, additi...
VoIP applications require the ability to identify speakers in real time. This paper presents Compressed Speaker Recognition (CSR), an innovative approach to perform speaker recogn...
Charu C. Aggarwal, David P. Olshefski, Debanjan Sa...
This paper presents a way to perform speaker adaptation for automatic speech recognition using the stream weights in a multi-stream setup, which included acoustic models for “Ar...
Person identification using audio (speech) and visual (facial appearance, static or dynamic) modalities, either independently or jointly, is a thoroughly investigated problem in pa...
In recent years, the proliferation of VOIP data has created a number of applications in which it is desirable to perform quick online classification and recognition of massive voi...