Jiahong Yuan


Automatically Detecting Reduced-formed English Pronunciations by Using Deep Learning
Lei Chen | Chenglin Jiang | Yiwei Gu | Yang Liu | Jiahong Yuan
Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)

Reduced form pronunciations are widely used by native English speakers, especially in casual conversations. Second language (L2) learners have difficulty in processing reduced form pronunciations in listening comprehension and face challenges in production too. Meanwhile, training applications dedicated to reduced forms are still few. To solve this issue, we report on our first effort of using deep learning to evaluate L2 learners’ reduced form pronunciations. Compared with a baseline solution that uses an ASR to determine regular or reduced-formed pronunciations, a classifier that learns representative features via a convolution neural network (CNN) on low-level acoustic features, yields higher detection performance. F-1 metric has been increased from $0.690$ to $0.757$ on the reduction task. Furthermore, adding word entities to compute attention weights to better adjust the features learned by the CNN model helps increasing F-1 to $0.763$.

Using Mixed Incentives to Document Xi’an Guanzhong
Juhong Zhan | Yue Jiang | Christopher Cieri | Mark Liberman | Jiahong Yuan | Yiya Chen | Odette Scharenborg
Proceedings of the 2nd Workshop on Novel Incentives in Data Collection from People: models, implementations, challenges and results within LREC 2022

This paper describes our use of mixed incentives and the citizen science portal LanguageARC to prepare, collect and quality control a large corpus of object namings for the purpose of providing speech data to document the under-represented Guanzhong dialect of Chinese spoken in the Shaanxi province in the environs of Xi’an.

Data Augmentation for the Post-Stroke Speech Transcription (PSST) Challenge: Sometimes Less Is More
Jiahong Yuan | Xingyu Cai | Kenneth Church
Proceedings of the RaPID Workshop - Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments - within the 13th Language Resources and Evaluation Conference

We employ the method of fine-tuning wav2vec2.0 for recognition of phonemes in aphasic speech. Our effort focuses on data augmentation, by supplementing data from both in-domain and out-of-domain datasets for training. We found that although a modest amount of out-of-domain data may be helpful, the performance of the model degrades significantly when the amount of out-of-domain data is much larger than in-domain data. Our hypothesis is that fine-tuning wav2vec2.0 with a CTC loss not only learns bottom-up acoustic properties but also top-down constraints. Therefore, out-of-domain data augmentation is likely to degrade performance if there is a language model mismatch between “in” and “out” domains. For in-domain audio without ground truth labels, we found that it is beneficial to exclude samples with less confident pseudo labels. Our final model achieves 16.7% PER (phoneme error rate) on the validation set, without using a language model for decoding. The result represents a relative error reduction of 14% over the baseline model trained without data augmentation. Finally, we found that “canonicalized” phonemes are much easier to recognize than manually transcribed phonemes.


On Attention Redundancy: A Comprehensive Study
Yuchen Bian | Jiaji Huang | Xingyu Cai | Jiahong Yuan | Kenneth Church
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Multi-layer multi-head self-attention mechanism is widely applied in modern neural language models. Attention redundancy has been observed among attention heads but has not been deeply studied in the literature. Using BERT-base model as an example, this paper provides a comprehensive study on attention redundancy which is helpful for model interpretation and model compression. We analyze the attention redundancy with Five-Ws and How. (What) We define and focus the study on redundancy matrices generated from pre-trained and fine-tuned BERT-base model for GLUE datasets. (How) We use both token-based and sentence-based distance functions to measure the redundancy. (Where) Clear and similar redundancy patterns (cluster structure) are observed among attention heads. (When) Redundancy patterns are similar in both pre-training and fine-tuning phases. (Who) We discover that redundancy patterns are task-agnostic. Similar redundancy patterns even exist for randomly generated token sequences. (“Why”) We also evaluate influences of the pre-training dropout ratios on attention redundancy. Based on the phase-independent and task-agnostic attention redundancy patterns, we propose a simple zero-shot pruning method as a case study. Experiments on fine-tuning GLUE tasks verify its effectiveness. The comprehensive analyses on attention redundancy make model understanding and zero-shot model pruning promising.


Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training
Renjie Zheng | Mingbo Ma | Baigong Zheng | Kaibo Liu | Jiahong Yuan | Kenneth Church | Liang Huang
Findings of the Association for Computational Linguistics: EMNLP 2020

Simultaneous speech-to-speech translation is an extremely challenging but widely useful scenario that aims to generate target-language speech only a few seconds behind the source-language speech. In addition, we have to continuously translate a speech of multiple sentences, but all recent solutions merely focus on the single-sentence scenario. As a result, current approaches will accumulate more and more latencies in later sentences when the speaker talks faster and introduce unnatural pauses into translated speech when the speaker talks slower. To overcome these issues, we propose Self-Adaptive Translation which flexibly adjusts the length of translations to accommodate different source speech rates. At similar levels of translation quality (as measured by BLEU), our method generates more fluent target speech latency than the baseline, in both Zh<->En directions.


Sentence selection for automatic scoring of Mandarin proficiency
Jiahong Yuan | Xiaoying Xu | Wei Lai | Weiping Ye | Xinru Zhao | Mark Liberman
Proceedings of the Eighth SIGHAN Workshop on Chinese Language Processing


A Cross-language Study on Automatic Speech Disfluency Detection
Wen Wang | Andreas Stolcke | Jiahong Yuan | Mark Liberman
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies