Xiang Hao
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
Xiang Hao has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
Guanglai Gao
College of Computer Science Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Inner Mongolia Univeristy Hohhot China
2 shared publicationsHuali Xu
College of Computer Science Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Inner Mongolia Univeristy Hohhot China
2 shared publications- Jibin Wu
The Hong Kong Polytechnic University
2 shared publications - Kay Chen Tan
The Hong Kong Polytechnic University
2 shared publications - Xiangdong Su
Inner Mongolia University
2 shared publications Zhiyu Wang
College of Computer Science Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Inner Mongolia Univeristy Hohhot China
2 shared publications
Latest Publications
- Top Cited Papers
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 18 (2) , 361-372
Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction
Humans can easily isolate a single speaker from a complex acoustic environment, a capability referred to as the “Cocktail Party Effect.” However, replicating this ability has been a significant challenge in the field of target speaker extraction (TSE). Traditional TSE approaches predominantly rely on voiceprints, which raise privacy concerns and face issues related to the quality and availability of enrollment samples, as well as intra-speaker variability. To address these issues, this work introduces a novel text-guided TSE paradigm named LLM-TSE. In this paradigm, a state-of-the-art large language model, LLaMA 2, processes typed text input from users to extract semantic cues. We demonstrate that textual descriptions alone can effectively serve as cues for extraction, thus addressing privacy concerns and reducing dependency on voiceprints. Furthermore, our approach offers flexibility by allowing the user to specify the extraction or suppression of a speaker and enhances robustness against intra-speaker variability by incorporating context-dependent textual information. Experimental results show competitive performance with text-based cues alone and demonstrate the effectiveness of using text as a task selector. Additionally, they achieve a new state-of-the-art when combining text-based cues with pre-registered cues. This work represents the first integration of LLMs with TSE, potentially establishing a new benchmark in solving the cocktail party problem and expanding the scope of TSE applications by providing a versatile, privacy-conscious solution. Demo is provided at https://github.com/LLM-TSE/llmtse.github.io
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 18 (2) , 361-372
Top Cited PapersTyping to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction
Humans can easily isolate a single speaker from a complex acoustic environment, a capability referred to as the “Cocktail Party Effect.” However, replicating this ability has been a significant challenge in the field of target speaker extraction (TSE). Traditional TSE approaches predominantly rely on voiceprints, which raise privacy concerns and face issues related to the quality and availability of enrollment samples, as well as intra-speaker variability. To address these issues, this work introduces a novel text-guided TSE paradigm named LLM-TSE. In this paradigm, a state-of-the-art large language model, LLaMA 2, processes typed text input from users to extract semantic cues. We demonstrate that textual descriptions alone can effectively serve as cues for extraction, thus addressing privacy concerns and reducing dependency on voiceprints. Furthermore, our approach offers flexibility by allowing the user to specify the extraction or suppression of a speaker and enhances robustness against intra-speaker variability by incorporating context-dependent textual information. Experimental results show competitive performance with text-based cues alone and demonstrate the effectiveness of using text as a task selector. Additionally, they achieve a new state-of-the-art when combining text-based cues with pre-registered cues. This work represents the first integration of LLMs with TSE, potentially establishing a new benchmark in solving the cocktail party problem and expanding the scope of TSE applications by providing a versatile, privacy-conscious solution. Demo is provided at https://github.com/LLM-TSE/llmtse.github.io
- Top Cited Papers
- 15 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (9) , 17350-17364
Toward Ultralow-Power Neuromorphic Speech Enhancement With Spiking-FullSubNet
Speech enhancement (SE) is critical for improving speech intelligibility and quality in various audio devices. In recent years, deep learning-based methods have significantly improved SE performance, but they often come with a high computational cost, which is prohibitive for a large number of edge devices, such as headsets and hearing aids. This work proposes an ultralow-power SE system based on the brain-inspired spiking neural network (SNN) called Spiking-FullSubNet. Spiking-FullSubNet follows a full-band and subband fusioned approach to effectively capture both global and local spectral information. To enhance the efficiency of computationally expensive subband modeling, we introduce a frequency partitioning method inspired by the sensitivity profile of the human peripheral auditory system. Furthermore, we introduce a novel spiking neuron model that can dynamically control the input information integration and forgetting, enhancing the multiscale temporal processing capability of SNN, which is critical for speech denoising. Experiments conducted on the recent Intel Neuromorphic Deep Noise Suppression (N-DNS) Challenge dataset show that the Spiking-FullSubNet surpasses state-of-the-art (SOTA) methods by large margins in terms of both speech quality and energy efficiency metrics. Notably, our system won the championship of the Intel N-DNS Challenge (algorithmic track), opening up a myriad of opportunities for ultralow-power SE at the edge. Our source code and model checkpoints are publicly available at github.com/haoxiangsnr/spiking-fullsubnet
- 15 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (9) , 17350-17364
Top Cited PapersToward Ultralow-Power Neuromorphic Speech Enhancement With Spiking-FullSubNet
Speech enhancement (SE) is critical for improving speech intelligibility and quality in various audio devices. In recent years, deep learning-based methods have significantly improved SE performance, but they often come with a high computational cost, which is prohibitive for a large number of edge devices, such as headsets and hearing aids. This work proposes an ultralow-power SE system based on the brain-inspired spiking neural network (SNN) called Spiking-FullSubNet. Spiking-FullSubNet follows a full-band and subband fusioned approach to effectively capture both global and local spectral information. To enhance the efficiency of computationally expensive subband modeling, we introduce a frequency partitioning method inspired by the sensitivity profile of the human peripheral auditory system. Furthermore, we introduce a novel spiking neuron model that can dynamically control the input information integration and forgetting, enhancing the multiscale temporal processing capability of SNN, which is critical for speech denoising. Experiments conducted on the recent Intel Neuromorphic Deep Noise Suppression (N-DNS) Challenge dataset show that the Spiking-FullSubNet surpasses state-of-the-art (SOTA) methods by large margins in terms of both speech quality and energy efficiency metrics. Notably, our system won the championship of the Intel N-DNS Challenge (algorithmic track), opening up a myriad of opportunities for ultralow-power SE at the edge. Our source code and model checkpoints are publicly available at github.com/haoxiangsnr/spiking-fullsubnet
- 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.
- Open Access
Pink-Eggs Dataset V1: A Step Toward Invasive Species Management Using Deep Learning Embedded Solutions
We introduce a novel dataset consisting of images depicting pink eggs that have been identified as Pomacea canaliculata eggs, accompanied by corresponding bounding box annotations. The purpose of this dataset is to aid researchers in the analysis of the spread of Pomacea canaliculata species by utilizing deep learning techniques, as well as supporting other investigative pursuits that require visual data pertaining to the eggs of Pomacea canaliculata. It is worth noting, however, that the identity of the eggs in question is not definitively established, as other species within the same taxonomic family have been observed to lay similar-looking eggs in regions of the Americas. Therefore, a crucial prerequisite to any decision regarding the elimination of these eggs would be to establish with certainty whether they are exclusively attributable to invasive Pomacea canaliculata or if other species are also involved. The dataset is available at https://www.kaggle.com/datasets/deeshenzhen/pinkeggs
Open AccessPink-Eggs Dataset V1: A Step Toward Invasive Species Management Using Deep Learning Embedded Solutions
We introduce a novel dataset consisting of images depicting pink eggs that have been identified as Pomacea canaliculata eggs, accompanied by corresponding bounding box annotations. The purpose of this dataset is to aid researchers in the analysis of the spread of Pomacea canaliculata species by utilizing deep learning techniques, as well as supporting other investigative pursuits that require visual data pertaining to the eggs of Pomacea canaliculata. It is worth noting, however, that the identity of the eggs in question is not definitively established, as other species within the same taxonomic family have been observed to lay similar-looking eggs in regions of the Americas. Therefore, a crucial prerequisite to any decision regarding the elimination of these eggs would be to establish with certainty whether they are exclusively attributable to invasive Pomacea canaliculata or if other species are also involved. The dataset is available at https://www.kaggle.com/datasets/deeshenzhen/pinkeggs
- Open Access
SNR-Based Teachers-Student Technique for Speech Enhancement
It is very challenging for speech enhancement methods to achieves robust performance under both high signal-to-noise ratio (SNR) and low SNR simultaneously. In this paper, we propose a method that integrates an SNR-based teachers-student technique and time-domain U-Net to deal with this problem. Specifically, this method consists of multiple teacher models and a student model. We first train the teacher models under multiple small-range SNRs that do not coincide with each other so that they can perform speech enhancement well within the specific SNR range. Then, we choose different teacher models to supervise the training of the student model according to the SNR of the training data. Eventually, the student model can perform speech enhancement under both high SNR and low SNR. To evaluate the proposed method, we constructed a dataset with an SNR ranging from -20dB to 20dB based on the public dataset. We experimentally analyzed the effectiveness of the SNR-based teachers-student technique and compared the proposed method with several state-of-the-art methods.
Open AccessSNR-Based Teachers-Student Technique for Speech Enhancement
It is very challenging for speech enhancement methods to achieves robust performance under both high signal-to-noise ratio (SNR) and low SNR simultaneously. In this paper, we propose a method that integrates an SNR-based teachers-student technique and time-domain U-Net to deal with this problem. Specifically, this method consists of multiple teacher models and a student model. We first train the teacher models under multiple small-range SNRs that do not coincide with each other so that they can perform speech enhancement well within the specific SNR range. Then, we choose different teacher models to supervise the training of the student model according to the SNR of the training data. Eventually, the student model can perform speech enhancement under both high SNR and low SNR. To evaluate the proposed method, we constructed a dataset with an SNR ranging from -20dB to 20dB based on the public dataset. We experimentally analyzed the effectiveness of the SNR-based teachers-student technique and compared the proposed method with several state-of-the-art methods.
- 9 December 2019
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 86-97
Learning an Adversarial Network for Speech Enhancement Under Extremely Low Signal-to-Noise Ratio Condition
- 9 December 2019
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 86-97
Learning an Adversarial Network for Speech Enhancement Under Extremely Low Signal-to-Noise Ratio Condition