Yicheng Gu
Research Subjects
Yicheng Gu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Zhizheng Wu
Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China
3 shared publications - Chaoren Wang
The Chinese University of Hong Kong, Shenzhen
2 shared publications - Chen Yang
Laboratory of Speech and Intelligent Information Processing, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China
1 shared publication - Dongjie Tang
Shanghai Customs College, Shanghai, China
1 shared publication - Fangxin Liu
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Haizhou Li
The Chinese University of Hong Kong, Shenzhen, China
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 1-16
Aliasing-Free Neural Audio Synthesis
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 1-16
Aliasing-Free Neural Audio Synthesis
- Top Cited Papers
- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 33, 4044-4054
Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation
Recent advancements in speech generation have been driven by large-scale training datasets. However, current models struggle to capture the spontaneity and variability inherent in real-world human speech, as they are primarily trained on audio-book datasets limited to formal, read-aloud speaking styles. To address this limitation, we introduce Emilia-Pipe, an open-source preprocessing pipeline designed to extract high-quality training data from valuable yet under-explored in-the-wild sources that capture spontaneous human speech in real-world contexts. Using Emilia-Pipe, we construct Emilia, which comprises over 101k hours of speech across six languages: English, Chinese, German, French, Japanese, and Korean. Furthermore, we expand Emilia to Emilia-Large, a dataset exceeding 216k hours, making it one of the largest open-source speech generation resources available. Extensive experiments show that Emilia-trained models produce markedly more spontaneous, human-like speech than those trained on traditional audio-book datasets, while matching their intelligibility. These models better capture diverse speaker timbres and the full spectrum of real-world conversational styles. Our work also highlights the importance of scaling dataset size for advancing speech generation performance and validates the effectiveness of Emilia for both multilingual and crosslingual speech generation tasks.
- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 33, 4044-4054
Top Cited PapersEmilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation
Recent advancements in speech generation have been driven by large-scale training datasets. However, current models struggle to capture the spontaneity and variability inherent in real-world human speech, as they are primarily trained on audio-book datasets limited to formal, read-aloud speaking styles. To address this limitation, we introduce Emilia-Pipe, an open-source preprocessing pipeline designed to extract high-quality training data from valuable yet under-explored in-the-wild sources that capture spontaneous human speech in real-world contexts. Using Emilia-Pipe, we construct Emilia, which comprises over 101k hours of speech across six languages: English, Chinese, German, French, Japanese, and Korean. Furthermore, we expand Emilia to Emilia-Large, a dataset exceeding 216k hours, making it one of the largest open-source speech generation resources available. Extensive experiments show that Emilia-trained models produce markedly more spontaneous, human-like speech than those trained on traditional audio-book datasets, while matching their intelligibility. These models better capture diverse speaker timbres and the full spectrum of real-world conversational styles. Our work also highlights the importance of scaling dataset size for advancing speech generation performance and validates the effectiveness of Emilia for both multilingual and crosslingual speech generation tasks.
- Open Access
- 21 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 22 (1) , 1-25
gCom: Fine-grained Compressors in Graphics Memory of Mobile GPU
Today, GPUs significantly boost rendering performance. However, the high memory requirements limit their use, especially on low-end mobile platforms. Compression techniques have been widely adopted to reduce memory consumption but face two primary issues when applied to mobile GPUs: (1) low repetition ratio caused by small raw data sizes and concurrency, and (2) low locality caused by unpredictable rendering behaviors. These two limitations result in a low compression ratio when compressors are applied to low-end mobile devices. This article introduces gCom , a fine-grained rendering compressor accelerated by GPUs. To improve the compression ratio, gCom incorporates the following innovations. First, unlike other compression techniques that use frames or tiles as basic processing units, gCom is the first to employ a fine-grained processing unit (i.e., the color channel), enhancing repetition amplification without increasing raw data. Second, gCom introduces two key features— Hierarchical Delta and Channel Decorrelator —which maximize the locality of adjacent channels and reduce raw data size. Third, to maintain the original GPU throughput, gCom revolutionizes the Golomb-Rice algorithm and proposes a new compression approach, the Parallel-Oriented Golomb-Rice algorithm, enabling parallel execution of both decompression and compression processes. The entire design of gCom utilizes only idle resources and existing commands on mobile GPUs, thus keeping purchasing costs low. To date, gCom has improved the channel locality by nearly 50%. The best compression achievement received by gCom has reached around 20%.
- 21 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 22 (1) , 1-25
Open AccessgCom: Fine-grained Compressors in Graphics Memory of Mobile GPU
Today, GPUs significantly boost rendering performance. However, the high memory requirements limit their use, especially on low-end mobile platforms. Compression techniques have been widely adopted to reduce memory consumption but face two primary issues when applied to mobile GPUs: (1) low repetition ratio caused by small raw data sizes and concurrency, and (2) low locality caused by unpredictable rendering behaviors. These two limitations result in a low compression ratio when compressors are applied to low-end mobile devices. This article introduces gCom , a fine-grained rendering compressor accelerated by GPUs. To improve the compression ratio, gCom incorporates the following innovations. First, unlike other compression techniques that use frames or tiles as basic processing units, gCom is the first to employ a fine-grained processing unit (i.e., the color channel), enhancing repetition amplification without increasing raw data. Second, gCom introduces two key features— Hierarchical Delta and Channel Decorrelator —which maximize the locality of adjacent channels and reduce raw data size. Third, to maintain the original GPU throughput, gCom revolutionizes the Golomb-Rice algorithm and proposes a new compression approach, the Parallel-Oriented Golomb-Rice algorithm, enabling parallel execution of both decompression and compression processes. The entire design of gCom utilizes only idle resources and existing commands on mobile GPUs, thus keeping purchasing costs low. To date, gCom has improved the channel locality by nearly 50%. The best compression achievement received by gCom has reached around 20%.
- 25 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 4569-4579
An Investigation of Time-Frequency Representation Discriminators for High-Fidelity Vocoders
Generative Adversarial Network (GAN) based vocoders are superior in both inference speed and synthesis quality when reconstructing an audible waveform from an acoustic representation. This study focuses on improving the discriminator for GAN-based vocoders. Most existing Time-Frequency Representation (TFR)-based discriminators are rooted in Short-Time Fourier Transform (STFT), which owns a constant Time-Frequency (TF) resolution, linearly scaled center frequencies, and a fixed decomposition basis, making it incompatible with signals like singing voices that require dynamic attention for different frequency bands and different time intervals. Motivated by that, we propose a Multi-Scale Sub-Band Constant-Q Transform CQT (MS-SB-CQT) discriminator and a Multi-Scale Temporal-Compressed Continuous Wavelet Transform CWT (MS-TC-CWT) discriminator. Both CQT and CWT have a dynamic TF resolution for different frequency bands. In contrast, CQT has a better modeling ability in pitch information, and CWT has a better modeling ability in short-time transients. Experiments conducted on both speech and singing voices confirm the effectiveness of our proposed discriminators. Moreover, the STFT, CQT, and CWT-based discriminators can be used jointly for better performance. The proposed discriminators can boost the synthesis quality of various state-of-the-art GAN-based vocoders, including HiFi-GAN, BigVGAN, and APNet.
- 25 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 4569-4579
An Investigation of Time-Frequency Representation Discriminators for High-Fidelity Vocoders
Generative Adversarial Network (GAN) based vocoders are superior in both inference speed and synthesis quality when reconstructing an audible waveform from an acoustic representation. This study focuses on improving the discriminator for GAN-based vocoders. Most existing Time-Frequency Representation (TFR)-based discriminators are rooted in Short-Time Fourier Transform (STFT), which owns a constant Time-Frequency (TF) resolution, linearly scaled center frequencies, and a fixed decomposition basis, making it incompatible with signals like singing voices that require dynamic attention for different frequency bands and different time intervals. Motivated by that, we propose a Multi-Scale Sub-Band Constant-Q Transform CQT (MS-SB-CQT) discriminator and a Multi-Scale Temporal-Compressed Continuous Wavelet Transform CWT (MS-TC-CWT) discriminator. Both CQT and CWT have a dynamic TF resolution for different frequency bands. In contrast, CQT has a better modeling ability in pitch information, and CWT has a better modeling ability in short-time transients. Experiments conducted on both speech and singing voices confirm the effectiveness of our proposed discriminators. Moreover, the STFT, CQT, and CWT-based discriminators can be used jointly for better performance. The proposed discriminators can boost the synthesis quality of various state-of-the-art GAN-based vocoders, including HiFi-GAN, BigVGAN, and APNet.