Papers by Qianqian Dong

7 papers
NeurST: Neural Speech Translation Toolkit (2021.acl-demo)

Copied to clipboard

Challenge: a toolkit for speech translation is available for free and provides step-by-step recipes for feature extraction, data preprocessing, distributed training, and evaluation.
Approach: They propose to use NeurST to facilitate speech translation research for NLP researchers . they show experimental results for different benchmark datasets which can be regarded as reliable baselines .
Outcome: The proposed framework provides reliable benchmarks for speech translation research.
MOSPC: MOS Prediction Based on Pairwise Comparison (2023.acl-short)

Copied to clipboard

Challenge: et al., 2016a) show that MOS prediction model can improve ranking accuracy of speech quality.
Approach: They propose a general framework for MOS prediction based on pair comparison . they use C-Mixup algorithm to enhance generalization performance of MOSPC .
Outcome: The proposed model outperforms baselines on most correlation coefficient metrics . it also surpasses the strong baseline in ranking accuracy on each fine-grained segment.
Parameter-Efficient Transfer Learning for End-to-end Speech Translation (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to improve end-to-end speech translation are limited by the availability of labeled data.
Approach: They propose a method which utilizes two lightweight adaptation techniques to modulate Attention and the Feed-Forward Network while preserving the capabilities of pre-trained models.
Outcome: The proposed method outperforms baseline models and significantly improves performance in low-resource settings.
CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Copied to clipboard

Challenge: Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach: They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome: The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .
CTC-based Non-autoregressive Speech Translation (2023.acl-long)

Copied to clipboard

Challenge: End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency.
Approach: They develop a model that uses connectionist temporal classification to predict the source and target texts.
Outcome: The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67.
Semi-Supervised Disfluency Detection (C18-1)

Copied to clipboard

Challenge: Detecting disfluency can be difficult because of the flexible nature of reparandum structure and the lack of a nested structure.
Approach: They propose a semi-supervised approach which extracts hidden features from self-attention without any Recurrent Neural Network (RNN) or Convolutional Neural Net (CNN).
Outcome: The proposed approach improves over baselines by using unlabelled data . identifying and removing non-fluent factors would help to improve spontaneous speech quality .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations