Searcharxiv⌕ Search

arXiv subjects

Hui Wang

Publications and source records attributed to Hui Wang.

At least 235 records · Page 13Linked to original sources
arXiv2025

Improving Zero-Shot Chinese-English Code-Switching ASR with kNN-CTC and Gated Monolingual Datastores

The kNN-CTC model has proven to be effective for monolingual automatic speech recognition (ASR). However, its direct application to multilingual scenarios like code-switching, presents challenges. Although there is potential for performance improvement, a kNN-CTC model utilizing a single bilingual datastore can inadvertently introduce undesirable noise from the alternative language. To address this, we propose a novel kNN-CTC-based code-switching ASR (CS-ASR) framework that employs dual monolingual datastores and a gated datastore selection mechanism to reduce noise interference. Our method selects the appropriate datastore for decoding each frame, ensuring the injection of language-specific information into the ASR process. We apply this framework to cutting-edge CTC-based models, developing an advanced CS-ASR system. Extensive experiments demonstrate the remarkable effectiveness of our gated datastore mechanism in enhancing the performance of zero-shot Chinese-English CS-ASR.

cs.CL↗
arXiv2025

Exploring Text-Queried Sound Event Detection with Audio Source Separation

In sound event detection (SED), overlapping sound events pose a significant challenge, as certain events can be easily masked by background noise or other events, resulting in poor detection performance. To address this issue, we propose the text-queried SED (TQ-SED) framework. Specifically, we first pre-train a language-queried audio source separation (LASS) model to separate the audio tracks corresponding to different events from the input audio. Then, multiple target SED branches are employed to detect individual events. AudioSep is a state-of-the-art LASS model, but has limitations in extracting dynamic audio information because of its pure convolutional structure for separation. To address this, we integrate a dual-path recurrent neural network block into the model. We refer to this structure as AudioSep-DP, which achieves the first place in DCASE 2024 Task 9 on language-queried audio source separation (objective single model track). Experimental results show that TQ-SED can significantly improve the SED performance, with an improvement of 7.22\% on F1 score over the conventional framework. Additionally, we setup comprehensive experiments to explore the impact of model complexity. The source code and pre-trained model are released at https://github.com/apple-yinhan/TQ-SED.

eess.AS↗
arXiv2025

MinMo: A Multimodal Large Language Model for Seamless Voice Interaction

Recent advancements in large language models (LLMs) and multimodal speech-text models have laid the groundwork for seamless voice interactions, enabling real-time, natural, and human-like conversations. Previous models for voice interactions are categorized as native and aligned. Native models integrate speech and text processing in one framework but struggle with issues like differing sequence lengths and insufficient pre-training. Aligned models maintain text LLM capabilities but are often limited by small datasets and a narrow focus on speech tasks. In this work, we introduce MinMo, a Multimodal Large Language Model with approximately 8B parameters for seamless voice interaction. We address the main limitations of prior aligned multimodal models. We train MinMo through multiple stages of speech-to-text alignment, text-to-speech alignment, speech-to-speech alignment, and duplex interaction alignment, on 1.4 million hours of diverse speech data and a broad range of speech tasks. After the multi-stage training, MinMo achieves state-of-the-art performance across various benchmarks for voice comprehension and generation while maintaining the capabilities of text LLMs, and also facilitates full-duplex conversation, that is, simultaneous two-way communication between the user and the system. Moreover, we propose a novel and simple voice decoder that outperforms prior models in voice generation. The enhanced instruction-following capabilities of MinMo supports controlling speech generation based on user instructions, with various nuances including emotions, dialects, and speaking rates, and mimicking specific voices. For MinMo, the speech-to-text latency is approximately 100ms, full-duplex latency is approximately 600ms in theory and 800ms in practice. The MinMo project web page is https://funaudiollm.github.io/minmo, and the code and models will be released soon.

cs.CL↗
arXiv2025

Planarian Neural Networks: Evolutionary Patterns from Basic Bilateria Shaping Modern Artificial Neural Network Architectures

This study examined the viability of enhancing the prediction accuracy of artificial neural networks (ANNs) in image classification tasks by developing ANNs with evolution patterns similar to those of biological neural networks. ResNet is a widely used family of neural networks with both deep and wide variants; therefore, it was selected as the base model for our investigation. The aim of this study is to improve the image classification performance of ANNs via a novel approach inspired by the biological nervous system architecture of planarians, which comprises a brain and two nerve cords. We believe that the unique neural architecture of planarians offers valuable insights into the performance enhancement of ANNs. The proposed planarian neural architecture-based neural network was evaluated on the CIFAR-10 and CIFAR-100 datasets. Our results indicate that the proposed method exhibits higher prediction accuracy than the baseline neural network models in image classification tasks. These findings demonstrate the significant potential of biologically inspired neural network architectures in improving the performance of ANNs in a wide range of applications.

cs.NE↗
arXiv2025

Dynamics of Meta-learning Representation in the Teacher-student Scenario

Gradient-based meta-learning algorithms have gained popularity for their ability to train models on new tasks using limited data. Empirical observations indicate that such algorithms are able to learn a shared representation across tasks, which is regarded as a key factor in their success. However, the in-depth theoretical understanding of the learning dynamics and the origin of the shared representation remains underdeveloped. In this work, we investigate the meta-learning dynamics of nonlinear two-layer neural networks trained on streaming tasks in the teacher-student scenario. Through the lens of statistical physics analysis, we characterize the macroscopic behavior of the meta-training processes, the formation of the shared representation, and the generalization ability of the model on new tasks. The analysis also points to the importance of the choice of certain hyperparameters of the learning algorithms.

cs.LG↗
arXiv2024

Enhancing Multimodal Emotion Recognition through Multi-Granularity Cross-Modal Alignment

Multimodal emotion recognition (MER), leveraging speech and text, has emerged as a pivotal domain within human-computer interaction, demanding sophisticated methods for effective multimodal integration. The challenge of aligning features across these modalities is significant, with most existing approaches adopting a singular alignment strategy. Such a narrow focus not only limits model performance but also fails to address the complexity and ambiguity inherent in emotional expressions. In response, this paper introduces a Multi-Granularity Cross-Modal Alignment (MGCMA) framework, distinguished by its comprehensive approach encompassing distribution-based, instance-based, and token-based alignment modules. This framework enables a multi-level perception of emotional information across modalities. Our experiments on IEMOCAP demonstrate that our proposed method outperforms current state-of-the-art techniques.

eess.AS↗
arXiv2024

Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision

Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persistent challenge. In this paper, we propose a novel self-supervised speaker verification approach, Self-Distillation Prototypes Network (SDPN), which effectively facilitates self-supervised speaker representation learning. SDPN assigns the representation of the augmented views of an utterance to the same prototypes as the representation of the original view, thereby enabling effective knowledge transfer between the augmented and original views. Due to lack of negative pairs in the SDPN training process, the network tends to align positive pairs quite closely in the embedding space, a phenomenon known as model collapse. To mitigate this problem, we introduce a diversity regularization term to embeddings in SDPN. Comprehensive experiments on the VoxCeleb datasets demonstrate the superiority of SDPN among self-supervised speaker verification approaches. SDPN sets a new state-of-the-art on the VoxCeleb1 speaker verification evaluation benchmark, achieving Equal Error Rate 1.80%, 1.99%, and 3.62% for trial VoxCeleb1-O, VoxCeleb1-E and VoxCeleb1-H, without using any speaker labels in training. Ablation studies show that both proposed learnable prototypes in self-distillation network and diversity regularization contribute to the verification performance.

eess.AS↗
arXiv2024

3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization

We introduce 3D-Speaker-Toolkit, an open-source toolkit for multimodal speaker verification and diarization, designed for meeting the needs of academic researchers and industrial practitioners. The 3D-Speaker-Toolkit adeptly leverages the combined strengths of acoustic, semantic, and visual data, seamlessly fusing these modalities to offer robust speaker recognition capabilities. The acoustic module extracts speaker embeddings from acoustic features, employing both fully-supervised and self-supervised learning approaches. The semantic module leverages advanced language models to comprehend the substance and context of spoken language, thereby augmenting the system's proficiency in distinguishing speakers through linguistic patterns. The visual module applies image processing technologies to scrutinize facial features, which bolsters the precision of speaker diarization in multi-speaker environments. Collectively, these modules empower the 3D-Speaker-Toolkit to achieve substantially improved accuracy and reliability in speaker-related tasks. With 3D-Speaker-Toolkit, we establish a new benchmark for multimodal speaker analysis. The toolkit also includes a handful of open-source state-of-the-art models and a large-scale dataset containing over 10,000 speakers. The toolkit is publicly available at https://github.com/modelscope/3D-Speaker.

eess.AS↗
arXiv2024

CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

In our previous work, we introduced CosyVoice, a multilingual speech synthesis model based on supervised discrete speech tokens. By employing progressive semantic decoding with two popular generative models, language models (LMs) and Flow Matching, CosyVoice demonstrated high prosody naturalness, content consistency, and speaker similarity in speech in-context learning. Recently, significant progress has been made in multi-modal large language models (LLMs), where the response latency and real-time factor of speech synthesis play a crucial role in the interactive experience. Therefore, in this report, we present an improved streaming speech synthesis model, CosyVoice 2, which incorporates comprehensive and systematic optimizations. Specifically, we introduce finite-scalar quantization to improve the codebook utilization of speech tokens. For the text-speech LM, we streamline the model architecture to allow direct use of a pre-trained LLM as the backbone. In addition, we develop a chunk-aware causal flow matching model to support various synthesis scenarios, enabling both streaming and non-streaming synthesis within a single model. By training on a large-scale multilingual dataset, CosyVoice 2 achieves human-parity naturalness, minimal response latency, and virtually lossless synthesis quality in the streaming mode. We invite readers to listen to the demos at https://funaudiollm.github.io/cosyvoice2.

cs.SD↗
arXiv2024

Boosted fusion gates above the percolation threshold for scalable graph-state generation

Fusing small resource states into a larger, fully connected graph-state is essential for scalable photonic quantum computing. Theoretical analysis reveals that this can only be achieved when the success probability of the fusion gate surpasses a specific percolation threshold of 58.98% by using three-photon GHZ states as resource states. However, such an implementation of a fusion gate has never been experimentally realized before. Here, we successfully demonstrate a boosted fusion gate with a theoretical success probability of 75%, using deterministically generated auxiliary states. The success probability is experimentally measured to be 71.0(7)%. We further demonstrate the effectiveness of the boosted fusion gate by fusing two Bell states with a fidelity of 67(2)%. Our work paves a crucial path toward scalable linear optical quantum computing.

quant-ph↗
arXiv2024

Ensuring Consistency for In-Image Translation

The in-image machine translation task involves translating text embedded within images, with the translated results presented in image format. While this task has numerous applications in various scenarios such as film poster translation and everyday scene image translation, existing methods frequently neglect the aspect of consistency throughout this process. We propose the need to uphold two types of consistency in this task: translation consistency and image generation consistency. The former entails incorporating image information during translation, while the latter involves maintaining consistency between the style of the text-image and the original image, ensuring background integrity. To address these consistency requirements, we introduce a novel two-stage framework named HCIIT (High-Consistency In-Image Translation) which involves text-image translation using a multimodal multilingual large language model in the first stage and image backfilling with a diffusion model in the second stage. Chain of thought learning is utilized in the first stage to enhance the model's ability to leverage image information during translation. Subsequently, a diffusion model trained for style-consistent text-image generation ensures uniformity in text style within images and preserves background details. A dataset comprising 400,000 style-consistent pseudo text-image pairs is curated for model training. Results obtained on both curated test sets and authentic image test sets validate the effectiveness of our framework in ensuring consistency and producing high-quality translated images.

cs.CL↗
arXiv2024

Achieving low contact resistance through copper-intercalated bilayer MoS$_2$

The high contact resistance between MoS$_2$ and metals hinders its potential as an ideal solution for overcoming the short channel effect in silicon-based FETs at sub-3nm scales. We theoretically designed a MoS$_2$-based transistor, featuring bilayer MoS$_2$ connected to Cu-intercalated bilayer MoS$_2$ electrodes. At 0.6 V, contact resistance is 16.7 $Ω\cdot μ$m (zigzag) and 30.0 $Ω\cdot μ$m (armchair), nearing or even surpassing the 30 $Ω\cdot μ$m quantum limit for single-layer materials. This low resistance is attributed to the elimination of the tunneling barrier and the creation of ohmic contacts. Additionally, the small contact potential difference enables lower operating voltages. Our intercalation design offers a novel approach to achieving low contact resistance in 2D electronic devices.

cond-mat.mes-hall↗
arXiv2024

COPR: Continual Human Preference Learning via Optimal Policy Regularization

Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences. Given the evolving nature of human preferences, continual alignment becomes more crucial and practical in comparison to traditional static alignment. Nevertheless, making RLHF compatible with Continual Learning (CL) is challenging due to its complex process. Meanwhile, directly learning new human preferences may lead to Catastrophic Forgetting (CF) of historical preferences, resulting in helpless or harmful outputs. To overcome these challenges, we propose the Continual Optimal Policy Regularization (COPR) method, which draws inspiration from the optimal policy theory. COPR utilizes a sampling distribution as a demonstration and regularization constraints for CL. It adopts the Lagrangian Duality (LD) method to dynamically regularize the current policy based on the historically optimal policy, which prevents CF and avoids over-emphasizing unbalanced objectives. We also provide formal proof for the learnability of COPR. The experimental results show that COPR outperforms strong CL baselines on our proposed benchmark, in terms of reward-based, GPT-4 evaluations and human assessment. Furthermore, we validate the robustness of COPR under various CL settings, including different backbones, replay memory sizes, and learning orders.

cs.LG↗
arXiv2024

Correcting Large Language Model Behavior via Influence Function

Recent advancements in AI alignment techniques have significantly improved the alignment of large language models (LLMs) with static human preferences. However, the dynamic nature of human preferences can render some prior training data outdated or even erroneous, ultimately causing LLMs to deviate from contemporary human preferences and societal norms. Existing methodologies, whether they involve the curation of new data for continual alignment or the manual correction of outdated data for re-alignment, demand costly human resources. To address this challenge, we propose a novel approach, Large Language Model Behavior Correction with Influence Function Recall and Post-Training (LANCET), which requires no human involvement. LANCET consists of two phases: (1) using influence functions to identify the training data that significantly impact undesirable model outputs, and (2) applying an Influence function-driven Bregman Optimization (IBO) technique to adjust the model's behavior based on these influence distributions. Our experiments demonstrate that LANCET effectively and efficiently correct inappropriate behaviors of LLMs. Furthermore, LANCET can outperform methods that rely on collecting human preferences, and it enhances the interpretability of learning human preferences within LLMs.

cs.LG↗
arXiv2024

Split Knowledge Distillation for Large Models in IoT: Architecture, Challenges, and Solutions

Large models (LMs) have immense potential in Internet of Things (IoT) systems, enabling applications such as intelligent voice assistants, predictive maintenance, and healthcare monitoring. However, training LMs on edge servers raises data privacy concerns, while deploying them directly on IoT devices is constrained by limited computational and memory resources. We analyze the key challenges of training LMs in IoT systems, including energy constraints, latency requirements, and device heterogeneity, and propose potential solutions such as dynamic resource management, adaptive model partitioning, and clustered collaborative training. Furthermore, we propose a split knowledge distillation framework to efficiently distill LMs into smaller, deployable versions for IoT devices while ensuring raw data remains local. This framework integrates knowledge distillation and split learning to minimize energy consumption and meet low model training delay requirements. A case study is presented to evaluate the feasibility and performance of the proposed framework.

cs.LG↗
arXiv2024

Controllable non-Hermitian qubit-qubit Coupling in Superconducting quantum Circuit

We propose a theoretical scheme to realize the controllable non-Hermitian qubit-qubit coupling by adding a high-loss resonator in tunable coupling superconducting quantum circuit. By changing the effective qubit-qubit coupling, phase and amplitude of resonator-qubit interaction, and the qubits' quantum states, we can continually tune the energy level attraction, position of EP (exceptional point), and the nonreciprocity in the non-Hermitian superconducting circuit. The EPs and non-reciprocity can affect the quantum states' evolutions and exchange efficiencies for two qubits in the non-Hermitian superconducting circuit. The controllable non-Hermitian and nonreciprocal interactions between two qubits provide a new insights and methods for exploring the unconventional quantum effects in superconducting quantum circuit.

quant-ph↗
arXiv2024

Addressing bias in Recommender Systems: A Case Study on Data Debiasing Techniques in Mobile Games

The mobile gaming industry, particularly the free-to-play sector, has been around for more than a decade, yet it still experiences rapid growth. The concept of games-as-service requires game developers to pay much more attention to recommendations of content in their games. With recommender systems (RS), the inevitable problem of bias in the data comes hand in hand. A lot of research has been done on the case of bias in RS for online retail or services, but much less is available for the specific case of the game industry. Also, in previous works, various debiasing techniques were tested on explicit feedback datasets, while it is much more common in mobile gaming data to only have implicit feedback. This case study aims to identify and categorize potential bias within datasets specific to model-based recommendations in mobile games, review debiasing techniques in the existing literature, and assess their effectiveness on real-world data gathered through implicit feedback. The effectiveness of these methods is then evaluated based on their debiasing quality, data requirements, and computational demands.

cs.LG↗