Michael Getty Horgan

Title: Michael Getty Horgan: Innovator in Speech Synthesis Technology

Introduction

Michael Getty Horgan is a notable inventor based in San Francisco, CA, recognized for his contributions to the field of speech synthesis technology. With a total of two patents to his name, he is making significant strides in advancing how machines can replicate and adapt human speech.

Latest Patents

Horgan's latest patents showcase his innovative approach to voice synthesis. The first patent, titled "Systems and methods for adapting human speaker embeddings in speech synthesis," reveals novel methods for voice cloning synthesizers that utilize real speech data to adapt a synthesizer to new speakers. His approach includes parameterizing utterances from target speakers, clustering utterance data, and employing neural networks to optimize the embedding vector for the synthesizer.

The second patent, "Speech style transfer," involves computer-implemented methods for synthesizing speech that accurately reflects the vocal traits of a source speaker while incorporating the style characteristics of a target speaker. This technology utilizes time-stamped phoneme sequences, pitch contour data, and speaker identification, supported by advanced neural networks for voice modeling and conditioning.

Career Highlights

Michael Getty Horgan is currently employed at Dolby Laboratories Licensing Corporation, where he applies his expertise in speech synthesis to develop innovative audio technologies. His work is pivotal in enhancing the consumer audio experience, and his patents illustrate his commitment to pushing the boundaries of what is technically possible in voice synthesis.

Collaborations

Throughout his career, Horgan has collaborated with talented colleagues, including Cong Zhou and Vivek Kumar. Their joint efforts in research and development at Dolby have helped foster advancements within the field, emphasizing the importance of teamwork in driving innovation.

Conclusion

As an inventor, Michael Getty Horgan continues to contribute to the evolving landscape of speech synthesis technology. With his innovative patents and collaborative spirit, his work is poised to have a lasting impact on how we interact with machines through voice.