Unmet Need
The 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 and text data.
Technology Overview
The inventors have developed speech and text autoencoders that share encoders and decoders with an automatic speech recognition (ASR) model to improve ASR performance with large speech only and text only training datasets. The experimental result obtained with their semi-supervised end-to-end ASR training revealed reductions from a model initially trained with a small paired subset of the LibriSpeech corpus in the character error rate from 10.4% to 8.4% and word error rate from 20.6% to 18.0% by retraining the model with a large unpaired subset of the corpus.
Stage of Development
Proof of concept testing has been completed.