13 citations · 126 across the 71 of their papers we have counts for
73 papers
Behavioral Probes for Information Flow in LLM Swarms
Junhui Chen, Yu Zhang, Lantian Li +1
Most existing approaches to LLM swarm optimization are utility-driven, focusing on final task utility while leaving the processing, integration, and reliance of information within…
Training-Free Multi-Step Inference for Target Speaker Extraction
Zhenghai You, Ying Shi, Lantian Li +1
Target speaker extraction (TSE) aims to recover a target speaker's speech from a mixture using a reference utterance as a cue. Most TSE systems adopt conditional auto-encoder archi…
MT-HuBERT: Self-Supervised Mix-Training for Few-Shot Keyword Spotting in Mixed Speech
Junming Yuan, Ying Shi, Dong Wang +2
Few-shot keyword spotting aims to detect previously unseen keywords with very limited labeled samples. A pre-training and adaptation paradigm is typically adopted for this task. Wh…
Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing
Zehua Liu, Xiaolou Li, Li Guo +2
Visual Speech Recognition (VSR) transcribes speech by analyzing lip movements. Recently, Large Language Models (LLMs) have been integrated into VSR systems, leading to notable perf…
CNVSRC 2024: The Second Chinese Continuous Visual Speech Recognition Challenge
Zehua Liu, Xiaolou Li, Chen Chen +2
This paper presents the second Chinese Continuous Visual Speech Recognition Challenge (CNVSRC 2024), which builds on CNVSRC 2023 to advance research in Chinese Large Vocabulary Con…
An Investigation on Speaker Augmentation for End-to-End Speaker Extraction
Zhenghai You, Zhenyu Zhou, Lantian Li +1
Target confusion, defined as occasional switching to non-target speakers, poses a key challenge for end-to-end speaker extraction (E2E-SE) systems. We argue that this problem is la…
AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition
Zehua Liu, Xiaolou Li, Chen Chen +3
Visual Speech Recognition (VSR) aims to recognize corresponding text by analyzing visual information from lip movements. Due to the high variability and weak information of lip mov…
Neural Scoring: A Refreshed End-to-End Approach for Speaker Recognition in Complex Conditions
Wan Lin, Junhui Chen, Tianhao Wang +3
Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and te…
Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective
Chen Chen, Xiaolou Li, Zehua Liu +2
In the field of spoken language processing, audio-visual speech processing is receiving increasing research attention. Key components of this research include tasks such as lip rea…
Few-Shot Keyword Spotting from Mixed Speech
Junming Yuan, Ying Shi, LanTian Li +2
Few-shot keyword spotting (KWS) aims to detect unknown keywords with limited training samples. A commonly used approach is the pre-training and fine-tuning framework. While effecti…
Serialized Output Training by Learned Dominance
Ying Shi, Lantian Li, Shi Yin +2
Serialized Output Training (SOT) has showcased state-of-the-art performance in multi-talker speech recognition by sequentially decoding the speech of individual speakers. To addres…
CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge
Chen Chen, Zehua Liu, Xiaolou Li +2
The first Chinese Continuous Visual Speech Recognition Challenge aimed to probe the performance of Large Vocabulary Continuous Visual Speech Recognition (LVC-VSR) on two tasks: (1)…
Zero-Shot Fake Video Detection by Audio-Visual Consistency
Xiaolou Li, Zehua Liu, Chen Chen +3
Recent studies have advocated the detection of fake videos as a one-class detection task, predicated on the hypothesis that the consistency between audio and visual modalities of g…
SE/BN Adapter: Parametric Efficient Domain Adaptation for Speaker Recognition
Tianhao Wang, Lantian Li, Dong Wang
Deploying a well-optimized pre-trained speaker recognition model in a new domain often leads to a significant decline in performance. While fine-tuning is a commonly employed solut…
A Comprehensive Investigation on Speaker Augmentation for Speaker Recognition
Zhenyu Zhou, Shibiao Xu, Shi Yin +2
Data augmentation (DA) has played a pivotal role in the success of deep speaker recognition. Current DA techniques primarily focus on speaker-preserving augmentation, which does no…
How phonemes contribute to deep speaker models?
Pengqi Li, Tianhao Wang, Lantian Li +2
Which phonemes convey more speaker traits is a long-standing question, and various perception experiments were conducted with human subjects. For speaker recognition, studies were…
Adversarial Data Augmentation for Robust Speaker Verification
Zhenyu Zhou, Junhui Chen, Namin Wang +2
Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulat…
A Glance is Enough: Extract Target Sentence By Looking at A keyword
Ying Shi, Dong Wang, Lantian Li +1
This paper investigates the possibility of extracting a target sentence from multi-talker speech using only a keyword as input. For example, in social security applications, the ke…
An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition
Zhenyu Zhou, Junhui Chen, Namin Wang +2
Multi-genre speaker recognition is becoming increasingly popular due to its ability to better represent the complexities of real-world applications. However, a major challenge is t…
Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification
Wan Lin, Lantian Li, Dong Wang
In real-world applications, speaker recognition models often face various domain-mismatch challenges, leading to a significant drop in performance. Although numerous domain adaptat…
Spot keywords from very noisy and mixed speech
Ying Shi, Dong Wang, Lantian Li +2
Most existing keyword spotting research focuses on conditions with slight or moderate noise. In this paper, we try to tackle a more challenging task: detecting keywords buried unde…
A Multi-Scale Attentive Transformer for Multi-Instrument Symbolic Music Generation
Xipin Wei, Junhui Chen, Zirui Zheng +3
Recently, multi-instrument music generation has become a hot topic. Different from single-instrument generation, multi-instrument generation needs to consider inter-track harmony b…
Visualizing data augmentation in deep speaker recognition
Pengqi Li, Lantian Li, Askar Hamdulla +1
Visualization is of great value in understanding the internal mechanisms of neural networks. Previous work found that LayerCAM is a reliable visualization tool for deep speaker mod…
Ordered and Binary Speaker Embedding
Jiaying Wang, Xianglong Wang, Namin Wang +2
Modern speaker recognition systems represent utterances by embedding vectors. Conventional embedding vectors are dense and non-structural. In this paper, we propose an ordered bina…