Yonghe Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yonghe Wang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Feilong Bao
Inner Mongolia University
3 shared publications - Guanglai Gao
Inner Mongolia University
2 shared publications Gaunglai Gao
College of Computer Science, Inner Mongolia University, China
1 shared publicationH. Maureen Kershaw
Natural Resources Canada
1 shared publication- Honglin Qu
College of Computer Science, Inner Mongolia University, Hohhot, China
1 shared publication - Hui Zhang
College of Computer Science, Inner Mongolia University, Hohhot, China
1 shared publication
Latest Publications
- Open Access
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Zero-Shot Speech Recognition from Text-Only Data through Synthesized Spectrogram Refinement Using Style Truncation and Contextual Alignment Loss
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessZero-Shot Speech Recognition from Text-Only Data through Synthesized Spectrogram Refinement Using Style Truncation and Contextual Alignment Loss
- Open Access
- 13 October 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (10) , 1-20
A Comparative Study on Selecting Acoustic Modeling Units for WFST-based Mongolian Speech Recognition
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.
- 13 October 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (10) , 1-20
Open AccessA Comparative Study on Selecting Acoustic Modeling Units for WFST-based Mongolian Speech Recognition
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.
- 23 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 30 (10709908) , 763-767
Noise-Separated Adaptive Feature Distillation for Robust Speech Recognition
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.
- 23 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 30 (10709908) , 763-767
Noise-Separated Adaptive Feature Distillation for Robust Speech Recognition
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.
- 6 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7788-7792
Joint Alignment Learning-Attention Based Model for Grapheme-to-Phoneme Conversion
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.
- 6 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7788-7792
Joint Alignment Learning-Attention Based Model for Grapheme-to-Phoneme Conversion
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.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1-3
DC-110GHz continuous variable attenuator based on 65nm CMOS process
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 .
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1-3
DC-110GHz continuous variable attenuator based on 65nm CMOS process
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 .
- 1 January 1996
- Published by Springer Nature in Environmental Monitoring and Assessment
- Vol. 39 (1-3) , 471-484
Tree species in relation to soil moisture regime in northwestern Ontario, Canada
Selected data on site, vegetation cover, and soil, including soil moisture regime (SMR), were collected from 2 167 field plots in northwestern Ontario, Canada. SMR provides an estimate of an averaged, “annualized” soil moisture supply throughout a complete vegetation cycle. SMR is based upon a relative scale that subjectively ranks sites from θ, 0, and 1 through 9 along a soil moisture continuum which relates to a dry to wet gradient. SMR may be generally correlated to tree growth, stand composition, degree of competition, nutrient availability and overall site quality. This paper reports on relationships between SMR and major tree species. Results highlight relationships between SMR class and the broad ecological ranges of several tree species. In northwestern Ontario, the determination of SMR can help resource managers to better understand the ecology of boreal sites.
- 1 January 1996
- Published by Springer Nature in Environmental Monitoring and Assessment
- Vol. 39 (1-3) , 471-484
Tree species in relation to soil moisture regime in northwestern Ontario, Canada
Selected data on site, vegetation cover, and soil, including soil moisture regime (SMR), were collected from 2 167 field plots in northwestern Ontario, Canada. SMR provides an estimate of an averaged, “annualized” soil moisture supply throughout a complete vegetation cycle. SMR is based upon a relative scale that subjectively ranks sites from θ, 0, and 1 through 9 along a soil moisture continuum which relates to a dry to wet gradient. SMR may be generally correlated to tree growth, stand composition, degree of competition, nutrient availability and overall site quality. This paper reports on relationships between SMR and major tree species. Results highlight relationships between SMR class and the broad ecological ranges of several tree species. In northwestern Ontario, the determination of SMR can help resource managers to better understand the ecology of boreal sites.