Company Filing History:
Years Active: 2013
Title: Innovations of Javier Latorre in Speech Synthesis
Introduction
Javier Latorre is a prominent inventor based in Tokyo, Japan. He has made significant contributions to the field of speech synthesis, holding a total of 3 patents. His work focuses on developing advanced methods and devices for generating synthetic speech.
Latest Patents
Latorre's latest patents include a speech synthesizer, a speech synthesizing method, and a program product. According to one embodiment, the speech synthesizer comprises an analyzer, a first estimator, a selector, a generator, a second estimator, and a synthesizer. The analyzer analyzes text and extracts linguistic features. The first estimator selects a first prosody model adapted to the linguistic feature and estimates prosody information that maximizes a first likelihood representing the probability of the selected first prosody model. The selector then selects speech units that minimize a cost function determined in accordance with the prosody information. The generator generates a second prosody model that represents the prosody information of the speech units. The second estimator estimates prosody information that maximizes a third likelihood calculated based on the first likelihood and a second likelihood representing the probability of the second prosody model. Finally, the synthesizer generates synthetic speech by concatenating the speech units based on the prosody information estimated by the second estimator.
Another notable patent involves separating speech waveforms into periodic and aperiodic components using an artificial waveform generated from pitch marks. In this embodiment, a speech processing device extracts a partial waveform from the speech signal. A calculator performs frequency analysis of the partial waveform to calculate a frequency spectrum. An estimator generates an artificial waveform according to the interval between the pitch marks for each harmonic component. This estimator also estimates harmonic spectral features representing characteristics of the frequency spectrum of the harmonic component from each of the artificial waveforms. A separator then separates the partial waveform into a periodic component produced from periodic vocal-fold vibration and an aperiodic component produced from other acoustic sources.
Career Highlights
Javier Latorre is currently employed at Kabushiki Kaisha Toshiba, where he continues to innovate in the field of speech technology. His work has garnered attention for its potential applications in various industries, including telecommunications and artificial intelligence.
Collaborations
Latorre has collaborated with notable coworkers such as Masami Akamine and Masahiro Morita, contributing to the advancement of speech synthesis