Jiaen Liang
Research Subjects
Jiaen Liang has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Yanhua Long
Shanghai Normal University Shanghai China
4 shared publications - Jianqing Sun
Unisound AI Technology Co., Ltd Beijing China
3 shared publications - Jinlong Xue
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications - Ya Li
Beijing University of Posts and Telecommunications
2 shared publications - Yayue Deng
Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications - Yijie Li
Unisound AI Technology Co., Ltd., Beijing, China
2 shared publications
Latest Publications
- Open Access
Semi-Supervised Facial Expression Recognition based on Dynamic Threshold and Negative Learning
Facial expression recognition is a key task in human-computer interaction and affective computing. However, acquiring a large amount of labeled facial expression data is often costly. Therefore, it is particularly important to design a semi-supervised facial expression recognition algorithm that makes full use of both labeled and unlabeled data. In this paper, we propose a semi-supervised facial expression recognition algorithm based on Dynamic Threshold Adjustment (DTA) and Selective Negative Learning (SNL). Initially, we designed strategies for local attention enhancement and random dropout of feature maps during feature extraction, which strengthen the representation of local features while ensuring the model does not overfit to any specific local area. Furthermore, this study introduces a dynamic thresholding method to adapt to the requirements of the semi-supervised learning framework for facial expression recognition tasks, and through a selective negative learning strategy, it fully utilizes unlabeled samples with low confidence by mining useful expression information from complementary labels, achieving impressive results. We have achieved state-of-the-art performance on the RAF-DB and AffectNet datasets. Our method surpasses fully supervised methods even without using the entire dataset, which proves the effectiveness of our approach.
Open AccessSemi-Supervised Facial Expression Recognition based on Dynamic Threshold and Negative Learning
Facial expression recognition is a key task in human-computer interaction and affective computing. However, acquiring a large amount of labeled facial expression data is often costly. Therefore, it is particularly important to design a semi-supervised facial expression recognition algorithm that makes full use of both labeled and unlabeled data. In this paper, we propose a semi-supervised facial expression recognition algorithm based on Dynamic Threshold Adjustment (DTA) and Selective Negative Learning (SNL). Initially, we designed strategies for local attention enhancement and random dropout of feature maps during feature extraction, which strengthen the representation of local features while ensuring the model does not overfit to any specific local area. Furthermore, this study introduces a dynamic thresholding method to adapt to the requirements of the semi-supervised learning framework for facial expression recognition tasks, and through a selective negative learning strategy, it fully utilizes unlabeled samples with low confidence by mining useful expression information from complementary labels, achieving impressive results. We have achieved state-of-the-art performance on the RAF-DB and AffectNet datasets. Our method surpasses fully supervised methods even without using the entire dataset, which proves the effectiveness of our approach.
- Open Access
Rhythm-controllable Attention with High Robustness for Long Sentence Speech Synthesis
Regressive Text-to-Speech (TTS) system utilizes attention mechanism to generate alignment between text and acoustic feature sequence. Alignment determines synthesis robustness (e.g, the occurence of skipping, repeating, and collapse) and rhythm via duration control. However, current attention algorithms used in speech synthesis cannot control rhythm using external duration information to generate natural speech while ensuring robustness. In this study, we propose Rhythm-controllable Attention (RC-Attention) based on Tracotron2, which improves robustness and naturalness simultaneously. Proposed attention adopts a trainable scalar learned from four kinds of information to achieve rhythm control, which makes rhythm control more robust and natural, even when synthesized sentences are extremely longer than training corpus. We use word errors counting and AB preference test to measure robustness of proposed method and naturalness of synthesized speech, respectively. Results shows that RC-Attention has the lowest word error rate of nearly 0.6%, compared with 11.8% for baseline system. Moreover, nearly 60% subjects prefer to the speech synthesized with RC-Attention to that with Forward Attention, because the former has more natural rhythm.
Open AccessRhythm-controllable Attention with High Robustness for Long Sentence Speech Synthesis
Regressive Text-to-Speech (TTS) system utilizes attention mechanism to generate alignment between text and acoustic feature sequence. Alignment determines synthesis robustness (e.g, the occurence of skipping, repeating, and collapse) and rhythm via duration control. However, current attention algorithms used in speech synthesis cannot control rhythm using external duration information to generate natural speech while ensuring robustness. In this study, we propose Rhythm-controllable Attention (RC-Attention) based on Tracotron2, which improves robustness and naturalness simultaneously. Proposed attention adopts a trainable scalar learned from four kinds of information to achieve rhythm control, which makes rhythm control more robust and natural, even when synthesized sentences are extremely longer than training corpus. We use word errors counting and AB preference test to measure robustness of proposed method and naturalness of synthesized speech, respectively. Results shows that RC-Attention has the lowest word error rate of nearly 0.6%, compared with 11.8% for baseline system. Moreover, nearly 60% subjects prefer to the speech synthesized with RC-Attention to that with Forward Attention, because the former has more natural rhythm.
- Open Access
ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis
In recent years, neural network based methods for multi-speaker text-to-speech synthesis (TTS) have made significant progress. However, the current speaker encoder models used in these methods still cannot capture enough speaker information. In this paper, we focus on accurate speaker encoder modeling and propose an end-to-end method that can generate high-quality speech and better similarity for both seen and unseen speakers. The proposed architecture consists of three separately trained components: a speaker encoder based on the state-of-the-art ECAPA-TDNN model which is derived from speaker verification task, a FastSpeech2 based synthesizer, and a HiFi-GAN vocoder. The comparison among different speaker encoder models shows our proposed method can achieve better naturalness and similarity. To efficiently evaluate our synthesized speech, we are the first to adopt deep learning based automatic MOS evaluation methods to assess our results, and these methods show great potential in automatic speech quality assessment.
Open AccessECAPA-TDNN for Multi-speaker Text-to-speech Synthesis
In recent years, neural network based methods for multi-speaker text-to-speech synthesis (TTS) have made significant progress. However, the current speaker encoder models used in these methods still cannot capture enough speaker information. In this paper, we focus on accurate speaker encoder modeling and propose an end-to-end method that can generate high-quality speech and better similarity for both seen and unseen speakers. The proposed architecture consists of three separately trained components: a speaker encoder based on the state-of-the-art ECAPA-TDNN model which is derived from speaker verification task, a FastSpeech2 based synthesizer, and a HiFi-GAN vocoder. The comparison among different speaker encoder models shows our proposed method can achieve better naturalness and similarity. To efficiently evaluate our synthesized speech, we are the first to adopt deep learning based automatic MOS evaluation methods to assess our results, and these methods show great potential in automatic speech quality assessment.
- 13 January 2022
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 25 (1) , 261-268
Exploring single channel speech separation for short-time text-dependent speaker verification
- 13 January 2022
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 25 (1) , 261-268
Exploring single channel speech separation for short-time text-dependent speaker verification
- 12 January 2022
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 25 (1) , 251-260
Acoustic domain mismatch compensation in bird audio detection
- 12 January 2022
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 25 (1) , 251-260
Acoustic domain mismatch compensation in bird audio detection
- Open Access
Self-and-Mixed Attention Decoder with Deep Acoustic Structure for Transformer-based LVCSR
The Transformer has shown impressive performance in automatic speech recognition. It uses the encoder-decoder structure with self-attention to learn the relationship between the high-level representation of the source inputs and embedding of the target outputs. In this paper, we propose a novel decoder structure that features a self-and-mixed attention decoder (SMAD) with a deep acoustic structure (DAS) to improve the acoustic representation of Transformer-based LVCSR. Specifically, we introduce a self-attention mechanism to learn a multi-layer deep acoustic structure for multiple levels of acoustic abstraction. We also design a mixed attention mechanism that learns the alignment between different levels of acoustic abstraction and its corresponding linguistic information simultaneously in a shared embedding space. The ASR experiments on Aishell-1 shown that the proposed structure achieves CERs of 4.8% on the dev set and 5.1% on the test set, which are the best results obtained on this task to the best of our knowledge.
Open AccessSelf-and-Mixed Attention Decoder with Deep Acoustic Structure for Transformer-based LVCSR
The Transformer has shown impressive performance in automatic speech recognition. It uses the encoder-decoder structure with self-attention to learn the relationship between the high-level representation of the source inputs and embedding of the target outputs. In this paper, we propose a novel decoder structure that features a self-and-mixed attention decoder (SMAD) with a deep acoustic structure (DAS) to improve the acoustic representation of Transformer-based LVCSR. Specifically, we introduce a self-attention mechanism to learn a multi-layer deep acoustic structure for multiple levels of acoustic abstraction. We also design a mixed attention mechanism that learns the alignment between different levels of acoustic abstraction and its corresponding linguistic information simultaneously in a shared embedding space. The ASR experiments on Aishell-1 shown that the proposed structure achieves CERs of 4.8% on the dev set and 5.1% on the test set, which are the best results obtained on this task to the best of our knowledge.
- 20 December 2019
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 23 (1) , 133-140
Mask-based blind source separation and MVDR beamforming in ASR
- 20 December 2019
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 23 (1) , 133-140
Mask-based blind source separation and MVDR beamforming in ASR
- 2 November 2018
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 38 (5) , 2320-2334
Speaker Direction-of-Arrival Estimation Based on Orthogonal Dipoles
- 2 November 2018
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 38 (5) , 2320-2334
Speaker Direction-of-Arrival Estimation Based on Orthogonal Dipoles