Company Filing History:
Years Active: 2016-2025
Title: Innovations of Srinivasa Rao Ponakala
Introduction
Srinivasa Rao Ponakala is an accomplished inventor based in Sunnyvale, CA. He has made significant contributions to the field of voice recognition technology, holding a total of 5 patents. His work focuses on enhancing the accuracy and reliability of voice assistants and automatic speech recognition systems.
Latest Patents
One of his latest patents is titled "System and method for speaker verification for voice assistant." This method involves obtaining audio data to identify a wake word or phrase. It generates an embedding vector based on the utterance and accesses previously-generated vectors representing earlier utterances. The method performs clustering to identify a cluster associated with a speaker and updates a speaker vector based on the embedding vector. It also determines a similarity score to verify if the speaker matches the identified cluster.
Another notable patent is "Context-aware false trigger mitigation for automatic speech recognition (ASR) systems or other systems." This method includes obtaining audio input and the location of an electronic device. It generates an audio embedding and determines differences between the audio embedding and a known user. The method assesses the probability of false triggers for automatic speech recognition and decides whether to perform recognition based on this probability.
Career Highlights
Srinivasa has worked with prominent companies such as Samsung Electronics and Quixey. His experience in these organizations has allowed him to develop innovative solutions in voice technology.
Collaborations
He has collaborated with talented individuals like Sivakumar Balasubramanian and Gowtham Srinivasan, contributing to advancements in his field.
Conclusion
Srinivasa Rao Ponakala's work in voice recognition technology showcases his innovative spirit and dedication to improving user experiences with voice assistants. His patents reflect a commitment to enhancing the functionality and reliability of speech recognition systems.