Yijie Li
Research Subjects
Yijie Li has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Yanhua Long
Shanghai Normal University Shanghai China
8 shared publications - Haoran Wei
Department of ECE, University of Texas at Dallas, Richardson, TX 75081, USA
2 shared publications - Jiaen Liang
Unisound AI Technology Co., Ltd Beijing China
2 shared publications - Dongxing Xu
Unisound AI Technology Co., Ltd., Beijing, China
1 shared publication - Hone Ye
Department of Electronical and Information Engineering, Shanghai Normal University, Shanghai, China
1 shared publication - Hongwei Mao
SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Normal University, Shanghai 200234, China
1 shared publication
Latest Publications
- 8 November 2023
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 26 (4) , 895-902
Boosting Character-based Mandarin ASR via Chinese Pinyin Representation
- 8 November 2023
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 26 (4) , 895-902
Boosting Character-based Mandarin ASR via Chinese Pinyin Representation
- 1 November 2023
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 26 (4) , 851-857
CI-Mix: cut instance mix for robust speaker verification
- 1 November 2023
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 26 (4) , 851-857
CI-Mix: cut instance mix for robust speaker verification
- Open Access
Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition
Low-resource accented speech recognition is one of the important challenges faced by current ASR technology in practical applications. In this study, we propose a Conformer-based architecture, called Aformer, to leverage both the acoustic information from large non-accented and limited accented training data. Specifically, a general encoder and an accent encoder are designed in the Aformer to extract complementary acoustic information. Moreover, we propose to train the Aformer in a multi-pass manner, and investigate three cross-information fusion methods to effectively combine the information from both general and accent encoders. All experiments are conducted on both the accented English and Mandarin ASR tasks. Results show that our proposed methods outperform the strong Conformer baseline by relative 10.2% to 24.5% word/character error rate reduction on six in-domain and out-of-domain accented test sets.
Open AccessMulti-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition
Low-resource accented speech recognition is one of the important challenges faced by current ASR technology in practical applications. In this study, we propose a Conformer-based architecture, called Aformer, to leverage both the acoustic information from large non-accented and limited accented training data. Specifically, a general encoder and an accent encoder are designed in the Aformer to extract complementary acoustic information. Moreover, we propose to train the Aformer in a multi-pass manner, and investigate three cross-information fusion methods to effectively combine the information from both general and accent encoders. All experiments are conducted on both the accented English and Mandarin ASR tasks. Results show that our proposed methods outperform the strong Conformer baseline by relative 10.2% to 24.5% word/character error rate reduction on six in-domain and out-of-domain accented test sets.
- Open Access
New Acoustic Features for Synthetic and Replay Spoofing Attack Detection
With the rapid development of intelligent speech technologies, automatic speaker verification (ASV) has become one of the most natural and convenient biometric speaker recognition approaches. However, most state-of-the-art ASV systems are vulnerable to spoofing attack techniques, such as speech synthesis, voice conversion, and replay speech. Due to the symmetry distribution characteristic between the genuine (true) speech and spoof (fake) speech pair, the spoofing attack detection is challenging. Many recent research works have been focusing on the ASV anti-spoofing solutions. This work investigates two types of new acoustic features to improve the performance of spoofing attacks. The first features consist of two cepstral coefficients and one LogSpec feature, which are extracted from the linear prediction (LP) residual signals. The second feature is a harmonic and noise subband ratio feature, which can reflect the interaction movement difference of the vocal tract and glottal airflow of the genuine and spoofing speech. The significance of these new features has been investigated in both the t-stochastic neighborhood embedding space and the binary classification modeling space. Experiments on the ASVspoof 2019 database show that the proposed residual features can achieve from 7% to 51.7% relative equal error rate (EER) reduction on the development and evaluation set over the best single system baseline. Furthermore, more than 31.2% relative EER reduction on both the development and evaluation set shows that the proposed new features contain large information complementary to the source acoustic features.
Open AccessNew Acoustic Features for Synthetic and Replay Spoofing Attack Detection
With the rapid development of intelligent speech technologies, automatic speaker verification (ASV) has become one of the most natural and convenient biometric speaker recognition approaches. However, most state-of-the-art ASV systems are vulnerable to spoofing attack techniques, such as speech synthesis, voice conversion, and replay speech. Due to the symmetry distribution characteristic between the genuine (true) speech and spoof (fake) speech pair, the spoofing attack detection is challenging. Many recent research works have been focusing on the ASV anti-spoofing solutions. This work investigates two types of new acoustic features to improve the performance of spoofing attacks. The first features consist of two cepstral coefficients and one LogSpec feature, which are extracted from the linear prediction (LP) residual signals. The second feature is a harmonic and noise subband ratio feature, which can reflect the interaction movement difference of the vocal tract and glottal airflow of the genuine and spoofing speech. The significance of these new features has been investigated in both the t-stochastic neighborhood embedding space and the binary classification modeling space. Experiments on the ASVspoof 2019 database show that the proposed residual features can achieve from 7% to 51.7% relative equal error rate (EER) reduction on the development and evaluation set over the best single system baseline. Furthermore, more than 31.2% relative EER reduction on both the development and evaluation set shows that the proposed new features contain large information complementary to the source acoustic features.
- 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
- 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
- Open Access
- 28 June 2019
- Published by MDPI AG in Applied Sciences
- Vol. 9 (13) , 2636
Addressing Text-Dependent Speaker Verification Using Singing Speech
The automatic speaker verification (ASV) has achieved significant progress in recent years. However, it is still very challenging to generalize the ASV technologies to new, unknown and spoofing conditions. Most previous studies focused on extracting the speaker information from natural speech. This paper attempts to address the speaker verification from another perspective. The speaker identity information was exploited from singing speech. We first designed and released a new corpus for speaker verification based on singing and normal reading speech. Then, the speaker discrimination was compared and analyzed between natural and singing speech in different feature spaces. Furthermore, the conventional Gaussian mixture model, the dynamic time warping and the state-of-the-art deep neural network were investigated. They were used to build text-dependent ASV systems with different training-test conditions. Experimental results show that the voiceprint information in the singing speech was more distinguishable than the one in the normal speech. More than relative 20% reduction of equal error rate was obtained on both the gender-dependent and independent 1 s-1 s evaluation tasks.
- 28 June 2019
- Published by MDPI AG in Applied Sciences
- Vol. 9 (13) , 2636
Open AccessAddressing Text-Dependent Speaker Verification Using Singing Speech
The automatic speaker verification (ASV) has achieved significant progress in recent years. However, it is still very challenging to generalize the ASV technologies to new, unknown and spoofing conditions. Most previous studies focused on extracting the speaker information from natural speech. This paper attempts to address the speaker verification from another perspective. The speaker identity information was exploited from singing speech. We first designed and released a new corpus for speaker verification based on singing and normal reading speech. Then, the speaker discrimination was compared and analyzed between natural and singing speech in different feature spaces. Furthermore, the conventional Gaussian mixture model, the dynamic time warping and the state-of-the-art deep neural network were investigated. They were used to build text-dependent ASV systems with different training-test conditions. Experimental results show that the voiceprint information in the singing speech was more distinguishable than the one in the normal speech. More than relative 20% reduction of equal error rate was obtained on both the gender-dependent and independent 1 s-1 s evaluation tasks.
- 1 February 2017
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 20 (1) , 171-178
Domain adaptation of lattice-free MMI based TDNN models for speech recognition
- 1 February 2017
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 20 (1) , 171-178
Domain adaptation of lattice-free MMI based TDNN models for speech recognition