Neural text-to-speech (TTS) generally consists of cascaded architecture with separately
optimized acoustic model and vocoder, or end-to-end architecture with continuous mel …

Contextualized end-to-end automatic speech recognition has been an active research area,
with recent efforts focusing on the implicit learning of contextual phrases based on the final …

Automatic Speech Recognition (ASR) still face challenges when recognizing time-variant
rare-phrases. Contextual biasing (CB) modules bias ASR model towards such contextually …

Automatic speech recognition (ASR) systems can suffer from poor recall for various reasons,
such as noisy audio, lack of sufficient training data, etc. Previous work has shown that recall …

Although contextualized automatic speech recognition (ASR) systems are commonly used to
improve the recognition of uncommon words, their effectiveness is hindered by the inherent …

Deep biasing (DB) improves the performance of end-to-end automatic speech recognition
(E2E-ASR) for rare words or contextual phrases using a bias list. However, most existing …

Correcting spelling mistakes is a complex task that presents significant challenges in
obtaining satisfactory solutions. In this study, we focus on Chinese spelling error correction …