An E2E-ASR-Based Iteratively-Trained Timestamp Estimator
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Signal Processing Letters"
DOI: 10.1109/lsp.2022.3190793
Abstract: Text-to-speech alignment, also known as time alignment, is essential for automatic speech recognition (ASR) systems used for speech retrieval tasks, such as keyword search and speech segment extraction. Previous works have used the Gaussian mixture… read more here.
Keywords: itse; speech; asr based; e2e asr ... See more keywords