Quoc Truong Do — accepted AI-conference papers

2023

AdapITN: A Fast, Reliable, and Dynamic Adaptive Inverse Text Normalization

Thai Binh Nguyen, Le Duc Minh Nhat, Quang Minh Nguyen, Quoc Truong Do, Chi Mai Luong, Alexander Waibel

ICASSP 2023accepted

Inverse text normalization (ITN) is the task that transforms text in spoken-form into written-form. While automatic speech recognition (ASR) produces text in spoken-form, human and natural language understanding systems prefer to consume text in written-form. ITN generally deals with semiotic phrase…

Cited by 0 Source ↗Scholar ↗

2015

WFST-based structural classification integrating dnn acoustic features and RNN language features for speech recognition

Quoc Truong Do, Satoshi Nakamura, Marc Delcroix, Takaaki Hori

ICASSP 2015accepted

This paper proposes a method to train Weighted Finite State Transducer (WFST) based structural classifiers using deep neural network (DNN) acoustic features and recurrent neural network (RNN) language features for speech recognition. Structural classification is an effective approach to achieve high…

Cited by 0 Source ↗Scholar ↗