Yonghe Wang

Yonghe Wang

Auto-generated profile, based on publicly available information

Yonghe Wang

College of Computer Science, Inner Mongolia University, Hohhot, China

Research Focus & Metrics

Academic Career Length

31Years (1996-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 1996 in Environmental Monitoring and Assessment
Verified
Journal Article
Closed access
PDF file
RSRichard A. Sims
Richard A. Sims
KBKenneth A. Baldwin
Kenneth A. Baldwin
HKH. Maureen Kershaw
H. Maureen Kershaw
YWYonghe Wang
Yonghe Wang

6 June 2021
Verified
Conference Paper
Closed access
YWYonghe Wang
Yonghe Wang
FBFeilong Bao
Feilong Bao
HZHui Zhang
Hui Zhang
GGGuanglai Gao
Guanglai Gao
Sequence-to-sequence attention-based models for grapheme-to-phoneme (G2P) conversion have gained significant interests. The attention-based encoder-decoder framework learns the mapping of input to output tokens by selectively focusing on relevant information, and has been shown well performance. However, the attention mechanism can result in non-monotonic alignments, resulting in poor G2P conversion performance. In this paper, we present a novel approach to optimize the G2P conversion model directly alignment grapheme-phoneme sequence by using alignment learning (AL) as the loss function. Besides, we propose a multi-task learning method that uses a joint alignment learning model and attention model to predict the proper alignments and thus improve the accuracy of G2P conversion. Evaluations on Mongolian and CMUDict tasks show that alignment learning as the loss function can effectively train G2P conversion model. Further, our multi-task method can significantly outperform both the alignment learning-based model and attention-based model.

23 June 2023 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
HQHonglin Qu
Honglin Qu
XSXiangdong Su
Xiangdong Su
YWYonghe Wang
Yonghe Wang
XHXiang Hao
Xiang Hao
GGGuanglai Gao
Guanglai Gao
This letter makes an improvement on feature-based knowledge distillation for robust speech recognition. The use of distillation techniques in speech recognition has been demonstrated to improve the robustness of the system. In this letter, we propose a noise-separated adaptive feature distillation method, including an adaptive distillation position selection strategy and a noise separation mechanism, assuming that there is a common network structure between the student and teacher. The proposed method has two improvements. First, distillation positions can be adaptively selected in each iteration by comparing loss values computed on intermediate representations of the student and the teacher, increasing the flexibility of knowledge transfer during distillation. Second, a noise separation module is proposed to constrain noise information elimination by explicitly separating the speech information and the noise information in noisy speech, which reduces the interference of noise information during distillation. Therefore, a better recognition performance is demonstrated with the proposed method compared to the standardized feature-based knowledge distillation method.

1 December 2017
Verified
Conference Paper
Closed access
Jiamei LvJiamei Lv
Jiamei Lv
JWJincai Wen
Jincai Wen
LWLong Wang
Long Wang
QZQingping Zhang
Qingping Zhang
YWYonghe Wang
Yonghe Wang
Continuous variable attenuator with wide bandwidth has been designed and fabricated in a 65nm CMOS process. This π-type with three shunt FETs in one side demonstrates state-of-the art performance showing a minimum insertion loss of 0.13-2.48 dB and good matching across the whole band. The attenuator has a continuous controllability from DC-110GHz with an attenuation range more than 16 dB as voltage bias changed constantly varies from 0 to 1.2V. Measurements also show return loss is greater than -22dB from 10 to 110GHz. The chip size is 340×280um 2 and the core area is 26×109um 2 .

13 October 2023 in ACM Transactions on Asian and Low-Resource Language Information Processing
Verified
Journal Article
Open access
WYWang Yonghe
Wang Yonghe
FBFeilong Bao
Feilong Bao
GGGaunglai Gao
Gaunglai Gao
Traditional weighted finite-state transducer– (WFST) based Mongolian automatic speech recognition (ASR) systems use phonemes as pronunciation lexicon modeling units. However, Mongolian is an agglutinative, low-resource language, and building an ASR system based on the phoneme pronunciation lexicon remains a challenge for various reasons. First, the phoneme pronunciation lexicon manually constructed by Mongolian linguists is finite, which is usually used to build a grapheme-to-phoneme conversion (G2P) model to frequently expand new words. However, the data sparsity decreases the robustness of the G2P model and affects the performance of the final ASR system. Second, homophones and polysyllabic words are common in Mongolian, which has a certain impact on the construction of the Mongolian acoustic model. To address these problems, in this work, we first propose a grapheme-to-phoneme alignment model to obtain the mapping relationship between phonemes and subword units. Then, we construct an acoustic subword segmentation set to segment words directly instead of using the traditional G2P method to predict phoneme sequences to expand the pronunciation lexicon. Further, by analyzing the Mongolian encoding form, we also propose an acoustic subword modeling units construction method that removes control characters. Finally, we investigate various acoustic subword modeling units for pronunciation lexicon construction for the Mongolian ASR system. Experiments on a Mongolian dataset with 325 hours of training show that the pronunciation lexicon based on the acoustic subword modeling unit can effectively construct the WFST-based Mongolian ASR system. Further, removing the control characters when building the acoustic subword modeling unit can further improve the ASR system performance.