Company Filing History:
Years Active: 2025
Title: Innovator Spotlight: Nilaksh Das
Introduction
Nilaksh Das is a prominent inventor based in Seattle, WA. He has made significant contributions to the field of automatic speech recognition, holding 2 patents that showcase his innovative approach to technology. His work focuses on enhancing the accuracy and efficiency of speech recognition systems.
Latest Patents
Nilaksh's latest patents include groundbreaking methods for infusing knowledge graphs into automatic speech recognition. This patent describes systems and methods for converting speech to text, which involves generating an initial transcript from audio or video files. The process includes extracting named entities using entity recognition and selecting a subset of nodes from a knowledge graph that correspond to these entities. The final transcript is produced by decoding the speech using generated entity embeddings.
Another notable patent addresses the removal of bias from automatic speech recognition models. This innovation utilizes internal language model estimates to enhance the accuracy of speech predictions. By processing audio data through an automatic speech recognition model and comparing original word token predictions with masked audio predictions, Nilaksh's method effectively reduces lexical bias in speech recognition.
Career Highlights
Nilaksh Das is currently employed at Amazon Technologies, Inc., where he continues to develop and refine technologies that improve user experiences in speech recognition. His work is instrumental in advancing the capabilities of automatic speech recognition systems.
Collaborations
Some of Nilaksh's coworkers include Monica Lakshmi Sunkara and Sravan Babu Bodapati, who contribute to the innovative environment at Amazon Technologies, Inc.
Conclusion
Nilaksh Das is a visionary inventor whose work in automatic speech recognition is paving the way for more accurate and efficient technologies. His contributions are significant in the realm of innovation, and his patents reflect a deep understanding of the complexities involved in speech processing.