Kiran Garaga Lokeswarappa

Title: Kiran Garaga Lokeswarappa: Innovator in Speech Recognition Technology

Introduction

Kiran Garaga Lokeswarappa is a prominent inventor based in Mountain View, CA, known for his contributions to speech recognition technology. With a total of seven patents to his name, he has made significant strides in the field of acoustic and linguistic feature extraction from speech audio.

Latest Patents

Among his latest patents is a method for deriving acoustic features and linguistic features from received speech audio. This computer-implemented method involves receiving speech audio associated with a user ID, deriving acoustic features, and storing them in a user profile. The method also includes receiving requests for these features through an API and sending the derived features accordingly. Another notable patent focuses on dynamic interpolation for hybrid language models, which aims to enhance the accuracy of automatic speech recognition (ASR). This innovation utilizes multiple language models to transcribe utterances, dynamically updating interpolation weights based on various contextual factors.

Career Highlights

Kiran has worked with notable companies such as SoundHound, Inc. and Walmart Apollo, LLC. His experience in these organizations has allowed him to refine his skills and contribute to cutting-edge technologies in speech recognition.

Collaborations

Throughout his career, Kiran has collaborated with talented individuals, including Bernard Mont-Reynaud and Jun Huang. These partnerships have fostered innovation and creativity in his projects.

Conclusion

Kiran Garaga Lokeswarappa's work in speech recognition technology exemplifies the impact of innovative thinking in the field. His patents and collaborations highlight his commitment to advancing technology and improving user experiences.