LabCompass

Kratika Bhagtani

Computer Science · Purdue University West Lafayette

OpenAlex ORCID
Early career · publishing since 2020Rising activity
Speech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio ProcessingTopic ModelingNatural Language Processing Techniques

Publications

28

Citations

193

Est. group size

~4

Recurring co-author estimate

Active years

7

Publishing since 2020

Research summary
AI-generated

Kratika Bhagtani works on detecting and analyzing AI-generated ('synthetic' or 'deepfake') speech, building datasets and machine learning models—often based on transformer and diffusion architectures—to identify, localize, and attribute fake audio, as well as to study fairness and robustness of these detection systems. The work also touches on speech recognition, audio forensics, and related applications like synthetic medical video generation.

Synthetic speech / deepfake audio detectionSpeech forensics and attributionTransformer and diffusion-based audio modelsFairness and robustness in speech detection systemsSpeech recognition and audio processing

Publication output was minimal before 2022 but has grown substantially since, peaking in 2023-2024, indicating a rapidly increasing and currently active research pace.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026

Publication cadence
Publications per year over the last 10 years — averaging 5.4/year recently
1718192020: 1 publication20212022: 3 publications222023: 8 publications232024: 12 publications12242025: 1 publication252026: 3 publications26
Recent publications
Publishes in
  • arXiv (Cornell University)×9
  • Electronic Imaging×1
  • bioRxiv (Cold Spring Harbor Laboratory)×1
Similar researchers
By research-topic overlap

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 20, 2026.

Claim or correct this profile