Marco Nicolis

Title: Marco Nicolis: Innovator in Audio Generation Technologies

Introduction

Marco Nicolis is a prominent inventor based in London, GB. He has made significant contributions to the field of audio generation technologies, holding 2 patents that showcase his innovative approach to enhancing synthesized speech.

Latest Patents

One of Nicolis's latest patents focuses on augmenting datasets for training audio generation models. This invention involves using speech prediction to enhance a target voice dataset. By training encoder and decoder models, Nicolis's approach encodes audio data into a format that retains semantic information, such as phonemes and words, along with feature data that indicates prosody, timbre, speaker identity, speech style, and emotion. The resulting acoustic/semantic language model (ASLM) predicts encoded speech data similarly to how traditional language models predict words. This technology allows for the generation of synthesized speech samples that closely resemble the characteristics of the target voice dataset, ultimately improving the performance of text-to-speech (TTS) models.

Another notable patent emphasizes portions of synthesized speech. This neural text-to-speech system is designed to apply emphasis to words, enhancing the prosodic characteristics of human speech. By making synthesized speech more understandable and engaging, Nicolis's invention addresses a common limitation in TTS systems. The emphasis can be manually annotated or predicted from source text, and the system may utilize generative models to create word acoustic embeddings that reflect how emphasis should be represented in the synthesized output.

Career Highlights

Marco Nicolis is currently employed at Amazon Technologies, Inc., where he continues to develop innovative solutions in audio generation. His work has positioned him as a key player in advancing TTS technologies.

Collaborations

Nicolis collaborates with talented individuals such as Mateusz Aleksander Lajszczak and Arent Van Korlaar, contributing to a dynamic team focused on pushing the boundaries of audio technology.

Conclusion

Marco Nicolis is a visionary inventor whose work in audio generation technologies is shaping the future of synthesized speech. His patents reflect a deep understanding of the complexities of human speech and the potential for technology to enhance communication.