Dan Su

Research on Cultivation Mode of Applied Talents Majoring in Computer of New Local Undergraduate Universities

2018 · 2018 4th International Conference on Education, Management and Information Technology (ICEMIT 2018)

In terms of the problems in the process of cultivating talents majoring in computer and characteristics of new local undergraduate colleges and universities, concrete measures have been discussed on employment-oriented talents who major in computer …

Speech-XLNet: Unsupervised Acoustic Model Pretraining for Self-Attention Networks

2020

Self-attention network (SAN) can benefit significantly from the bi-directional representation learning through unsupervised pretraining paradigms such as BERT and XLNet.In this paper, we present an XLNet-like pretraining scheme "Speech-XLNet" to learn speech representations with self-attention …

Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling

2021 · arXiv (Cornell University)

Comparing with traditional text-to-speech (TTS) systems, conversational TTS systems are required to synthesize speeches with proper speaking style confirming to the conversational context. However, state-of-the-art context modeling methods in conversational TTS only model the textual …

NusaCrowd: Open Source Initiative for Indonesian NLP Resources

2022 · arXiv (Cornell University)

We present NusaCrowd, a collaborative initiative to collect and unify existing resources for Indonesian languages, including opening access to previously non-public resources. Through this initiative, we have brought together 137 datasets and 118 standardized data …

Trinet: Stabilizing Self-Supervised Learning From Complete or Slow Collapse

2023

Self-supervised learning (SSL) models confront challenges of abrupt informational collapse or slow dimensional collapse. We propose TriNet, which introduces a novel triple-branch architecture for preventing collapse and stabilizing the pretraining. TriNet learns the SSL latent …

Investigating End-to-end Speech Recognition for Mandarin-english Code-switching

2019

Code-switching is a common phenomenon in many multilingual communities and presents a challenge to automatic speech recognition (ASR). In this paper, three approaches are investigated to improve end-to-end speech recognition on Mandarin-English code-switching task. First, …

Survey of Hallucination in Natural Language Generation

2022 · ACM Computing Surveys

Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading …

A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity

2023 · arXiv (Cornell University)

This paper proposes a framework for quantitatively evaluating interactive LLMs such as ChatGPT using publicly available data sets. We carry out an extensive technical evaluation of ChatGPT using 23 data sets covering 8 different common …