Aviral Anshu is a prominent inventor based in Mountain View, CA (US). He has made significant contributions to the field of speech processing, holding 2 patents that showcase his innovative approach to technology.

Latest Patents

One of Aviral's latest patents is titled "Method and apparatus for performing speaker diarization on mixed-bandwidth speech signals." This invention involves an apparatus for processing speech data, which includes a processor designed to separate input speech into distinct speech signals. The processor identifies the bandwidth of each speech signal, extracts speaker embeddings using neural networks, and clusters these embeddings into speaker identities.

Another notable patent is "System and method for context-enriched attentive memory network with global and local encoding for dialogue breakdown detection." This method involves obtaining verbal input from an audio sensor and generating a reply. It identifies local and global contexts from the verbal input and previous interactions, detecting dialogue breakdowns when the reply does not align with these contexts. The system generates sound corresponding to the reply when no breakdown is identified.

Career Highlights

Aviral Anshu is currently employed at Samsung Electronics Co., Ltd., where he continues to develop innovative solutions in speech technology. His work has positioned him as a key player in advancing the capabilities of dialogue systems and speech processing.

Collaborations

Aviral collaborates with talented individuals such as Alireza Dirafzoon and Myungjong Kim, contributing to a dynamic team focused on cutting-edge technology.

Conclusion

Aviral Anshu's contributions to speech processing through his patents reflect his dedication to innovation and technology. His work at Samsung Electronics Co., Ltd. continues to influence the field significantly.