Ramin Pishehvar

Title: Ramin Pishehvar: Innovator in Machine Learning and Audio Processing

Introduction

Ramin Pishehvar is a prominent inventor based in Los Angeles, CA. He has made significant contributions to the fields of machine learning and audio processing, holding a total of 7 patents. His work focuses on enhancing speech signals and improving audio quality through innovative technologies.

Latest Patents

One of Ramin's latest patents is titled "End-to-end time-domain multitask learning for ML-based speech enhancement." This invention discloses a multi-task machine learning model, specifically a time-domain deep neural network (DNN), that generates an enhanced target speech signal and target audio parameters from a mixed signal of target speech and interference. The DNN encodes the mixed signal, determines masks for estimating the target signal and audio parameters, and applies these masks to separate the target speech from interference. Additionally, the DNN leverages multi-channel audio and multi-modal signals, such as video, to enhance the robustness of the target speech signal.

Another notable patent is "Spatially informed acoustic echo cancelation." This invention captures multiple microphone signals and determines echo-dominant audio signals based on a directed pick-up beam towards speakers. By using these echo-dominant signals as a reference, the invention effectively removes unwanted sound emitted from speakers, resulting in clean audio output.

Career Highlights

Ramin Pishehvar is currently employed at Apple Inc., where he continues to innovate and develop cutting-edge technologies. His work has significantly impacted the way audio processing is approached in modern devices.

Collaborations

Ramin has collaborated with notable coworkers, including Joshua D Atkins and Mehrez Souden, contributing to various projects that enhance audio and machine learning technologies.

Conclusion

Ramin Pishehvar is a key figure in the realm of machine learning and audio processing, with a strong portfolio of patents that reflect his innovative spirit. His contributions continue to shape the future of audio technology and machine learning applications.