27 citations · 27 across the 3 of their papers we have counts for
6 papers
FROST-EMA: Finnish and Russian Oral Speech Dataset of Electromagnetic Articulography Measurements with L1, L2 and Imitated L2 Accents
Satu Hopponen, Tomi Kinnunen, Alexandre Nikolaev +3
We introduce a new FROST-EMA (Finnish and Russian Oral Speech Dataset of Electromagnetic Articulography) corpus. It consists of 18 bilingual speakers, who produced speech in their…
Gamified Speaker Comparison by Listening
Sandip Ghimire, Tomi Kinnunen, Rosa Gonzalez Hautamäki
We address speaker comparison by listening in a game-like environment, hypothesized to make the task more motivating for naive listeners. We present the same 30 trials selected wit…
Improving speaker de-identification with functional data analysis of f0 trajectories
Lauri Tavi, Tomi Kinnunen, Rosa González Hautamäki
Due to a constantly increasing amount of speech data that is stored in different types of databases, voice privacy has become a major concern. To respond to such concern, speech re…
Why Did the x-Vector System Miss a Target Speaker? Impact of Acoustic Mismatch Upon Target Score on VoxCeleb Data
Rosa González Hautamäki, Tomi Kinnunen
Modern automatic speaker verification (ASV) relies heavily on machine learning implemented through deep neural networks. It can be difficult to interpret the output of these black…
Voice Mimicry Attacks Assisted by Automatic Speaker Verification
Ville Vestman, Tomi Kinnunen, Rosa González Hautamäki +1
In this work, we simulate a scenario, where a publicly available ASV system is used to enhance mimicry attacks against another closed source ASV system. In specific, ASV technology…
Can We Use Speaker Recognition Technology to Attack Itself? Enhancing Mimicry Attacks Using Automatic Target Speaker Selection
Tomi Kinnunen, Rosa González Hautamäki, Ville Vestman +1
We consider technology-assisted mimicry attacks in the context of automatic speaker verification (ASV). We use ASV itself to select targeted speakers to be attacked by human-based…