Search Results - speech+processing+software

2 Results

Sort By:

Neural Diarization based on Permutation-invariant Training

Unmet NeedSpeech enhancement and speaker-adaption are essential for several applications, specifically those with much noise that make hearing sounds and differentiating noises difficult. This environment, called an overlapping speech environment, can be broken down into two categories of level of effect and how much the hearing is influenced negatively....

Published: 9/27/2024 | Inventor(s): Shinji Watanabe, Yusuke Fujita, Takeshi Kanai, Daisuke Mizumoto

Keywords(s): Computer and Network Systems, Computer Software, Parallel Computing Software, Speech Processing Software

Category(s): Technology Classifications > Computers, Electronics & Software > Machine Learning, Technology Classifications > Computers, Electronics & Software > Algorithms

Semi-supervised end-to-end speech recognition using text-to-speech and autoencoders

Unmet NeedThe speech and voice recognition market is set to reach 25 B at 20% CAGR through 2025. The development of software with low error rate and fast conversion between speech and text has been of great interest. Specifically, there is a need for speech and text encoders for speech only or text only datasets without the need for parallel speech...

Published: 9/27/2024 | Inventor(s): Shinji Watanabe, Shigeki Karita, Iwata Tomoharu, Atsunori Ogawa, Tomohiro Nakatani

Keywords(s): Computer and Network Systems, Computer Software, Speech Processing Software

Category(s): Technology Classifications > Computers, Electronics & Software > Algorithms, Technology Classifications > Computers, Electronics & Software > Artificial Intelligence, Technology Classifications > Computers, Electronics & Software > Machine Learning