Haihua Xu

On statistical machine translation method for lexicon refinement in speech recognition

2015

In low resource Automatic Speech Recognition (ASR), one usually resorts to the Statistical Machine Translation (SMT) technique to learn transform rules to refine grapheme lexicon. To do this, we face two challenges. One is to …

Improving code-switching speech recognition with data augmentation and system combination

2019

We focused on a study of comprehensive approaches to an improved code-switching speech recognition, using data augmentation and system combination methods. For data augmentation, we not only use speech speed perturbation based method, but we …

Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-switching Speech Recognition

2020 · arXiv (Cornell University)

In this paper, we conduct data selection analysis in building an English-Mandarin code-switching (CS) speech recognition (CSSR) system, which is aimed for a real CSSR contest in China. The overall training sets have three subsets, …

The NTU-AISG Text-to-speech System for Blizzard Challenge 2020

2020 · arXiv (Cornell University)

We report our NTU-AISG Text-to-speech (TTS) entry systems for the Blizzard Challenge 2020 in this paper. There are two TTS tasks in this year's challenge, one is a Mandarin TTS task, the other is a …

Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data

2019

The lack of code-switch training data is one of the major concerns in the development of end-to-end code-switching automatic speech recognition (ASR) models. In this work, we propose a method to train an improved end-to-end …