June 11, 2024, 4:47 a.m. | Shlomo Salo Elia, Aviad Malachi, Vered Aharonson, Gadi Pinkas

cs.LG updates on arXiv.org arxiv.org

arXiv:2406.05863v1 Announce Type: cross
Abstract: Domain adaptation is often hampered by exceedingly small target datasets and inaccessible source data. These conditions are prevalent in speech verification, where privacy policies and/or languages with scarce speech resources limit the availability of sufficient data. This paper explored techniques of sourcefree domain adaptation unto a limited target speech dataset for speaker verificationin data-scarce languages. Both language and channel mis-match between source and target were investigated. Fine-tuning methods were evaluated and compared across different sizes …

abstract arxiv availability channels cs.lg cs.sd data datasets domain domain adaptation eess.as free languages paper policies privacy privacy policies resources small source data speaker speech type verification

Senior Data Engineer

@ Displate | Warsaw

Solution Architect

@ Philips | Bothell - B2 - Bothell 22050

Senior Product Development Engineer - Datacenter Products

@ NVIDIA | US, CA, Santa Clara

Systems Engineer - 2nd Shift (Onsite)

@ RTX | PW715: Asheville Site W Asheville Greenfield Site TBD , Asheville, NC, 28803 USA

System Test Engineers (HW & SW)

@ Novanta | Barcelona, Spain

Senior Solutions Architect, Energy

@ NVIDIA | US, TX, Remote