Jayati Tripathi

Title: Innovations by Jayati Tripathi in Audio Speech Signal Analysis

Introduction

Jayati Tripathi is an accomplished inventor based in Bengaluru, India. He has made significant contributions to the field of audio speech signal analysis, particularly in the context of fraud detection. His innovative approach combines advanced machine learning techniques to enhance the security of contact centers.

Latest Patents

Jayati Tripathi holds a patent for a groundbreaking invention titled "Audio speech signal analysis for fraud detection." This patent describes a device, system, and method for analyzing audio speech signals to detect fraudulent calls to a contact center. The invention involves splitting an audio recording of a call in real-time into a foreground speech signal attributed to the main speaker and a background audio signal. It extracts audio features from both signals and inputs them into an ensemble model comprising multiple different machine learning models co-trained to cumulatively detect fraud. The models include a speaker audio model to detect audio speech anomalies, a speaker intent model to classify the intent of the main speaker, a synthetic voice detection model to identify non-human entities, and a prosody model to detect the voice intonation of the main speaker. The ensemble model outputs a prediction indicating whether the call is fraudulent.

Career Highlights

Jayati Tripathi is currently employed at Morgan Stanley Services Group Inc., where he applies his expertise in audio signal processing and machine learning. His work focuses on developing innovative solutions that enhance the efficiency and security of communication systems.

Collaborations

Throughout his career, Jayati has collaborated with talented professionals, including Sushil Ninawe and Cheryl Fernandes. These collaborations have contributed to the advancement of his projects and the successful implementation of his inventions.

Conclusion

Jayati Tripathi's contributions to audio speech signal analysis represent a significant advancement in fraud detection technology. His innovative patent showcases the potential of machine learning in enhancing security measures within contact centers.