Company Filing History:
Years Active: 2023-2024
Title: Simon Slangen: Innovator in Speech Processing Technologies
Introduction
Simon Slangen is a prominent inventor based in Edinburgh, GB. He has made significant contributions to the field of speech processing, holding a total of 3 patents. His work focuses on utilizing advanced neural networks to enhance the quality and efficiency of synthesized speech.
Latest Patents
One of Simon's latest patents is titled "Synthetic speech processing by representing text by phonemes exhibiting predicted volume and pitch using neural networks." This innovative speech-processing system receives input data representing text and employs encoders trained to predict audio properties corresponding to the text. The system processes the text to predict those properties, and a speech decoder then creates data representing synthesized speech.
Another notable patent is "Multi-scale spectrogram text-to-speech." This patent describes techniques for performing text-to-speech, including generating audio from input text by predicting one or more spectrograms using multiple scales. The method involves concatenating vectors and predicted spectrograms to generate audio output, showcasing Simon's expertise in the field.
Career Highlights
Simon Slangen is currently employed at Amazon Technologies, Inc., where he continues to develop cutting-edge technologies in speech processing. His work at Amazon has allowed him to push the boundaries of what is possible in the realm of synthesized speech.
Collaborations
Throughout his career, Simon has collaborated with talented individuals such as Syed Ammar Abbas and Thomas Renaud Drugman. These collaborations have contributed to the advancement of his projects and the successful development of innovative solutions in speech technology.
Conclusion
Simon Slangen is a key figure in the field of speech processing, with a focus on neural network applications. His patents reflect his commitment to innovation and excellence in technology. His contributions continue to shape the future of synthesized speech.