Zejun Ma

A Unified Sequence-to-Sequence Front-End Model for Mandarin Text-to-Speech Synthesis

2020

In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech. Building a typical pipeline-based front-end which consists of multiple individual components requires extensive efforts. In this …

Improving Non-native Word-level Pronunciation Scoring with Phone-level Mixup Data Augmentation and Multi-source Information

2022 · arXiv (Cornell University)

Deep learning-based pronunciation scoring models highly rely on the availability of the annotated non-native data, which is costly and has scalability issues. To deal with the data scarcity problem, data augmentation is commonly used for …

Improving Pseudo-label Training For End-to-end Speech Recognition Using Gradient Mask

2021 · arXiv (Cornell University)

In the recent trend of semi-supervised speech recognition, both self-supervised representation learning and pseudo-labeling have shown promising results. In this paper, we propose a novel approach to combine their ideas for end-to-end speech recognition model. …

CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-Training

2023 · arXiv (Cornell University)

Speech or text representation generated by pre-trained models contains modal-specific information that could be combined for benefiting spoken language understanding (SLU) tasks. In this work, we propose a novel pre-training paradigm termed Continuous Integrate-and-Fire Pre-Training …