Manish Kumar Sharma

Title: Manish Kumar Sharma: Innovator in Speech Synthesis Technology

Introduction

Manish Kumar Sharma is a prominent inventor based in London, GB. He has made significant contributions to the field of speech synthesis, holding two patents that showcase his innovative approach to technology. His work focuses on enhancing the quality and naturalness of synthetic speech, which has important applications in various industries.

Latest Patents

One of Manish's latest patents is titled "Speech synthesis prosody using a BERT model." This method involves generating a prosodic representation of text utterances by utilizing a Bidirectional Encoder Representations from Transformers (BERT) model. The process includes generating wordpiece embeddings and selecting an utterance embedding that represents the intended prosody. This innovative approach allows for more accurate predictions of syllable durations by encoding linguistic features of phonemes.

Another notable patent is "Self-training WaveNet for text-to-speech." This method involves training an autoregressive neural network using recorded speech samples to produce synthetic speech. The process includes generating synthetic speech samples and further training a second autoregressive neural network, which is distilled into a feedforward neural network. This advancement in text-to-speech technology enhances the quality of synthetic voices, making them more lifelike.

Career Highlights

Manish Kumar Sharma is currently employed at Google Inc., where he continues to push the boundaries of speech synthesis technology. His work at Google allows him to collaborate with some of the brightest minds in the industry, contributing to groundbreaking advancements in artificial intelligence and machine learning.

Collaborations

Some of Manish's notable coworkers include Tom Marius Kenter and Robert Clark. Their collaborative efforts in research and development have further enriched the innovative environment at Google Inc.

Conclusion

Manish Kumar Sharma is a key figure in the field of speech synthesis, with patents that reflect his commitment to innovation. His work not only enhances the capabilities of synthetic speech but also paves the way for future advancements in technology.