Liang He

Yuhao Dan, Zhikai Lei, Yiyang Gu et al.

EduChat (https://www.educhat.top/) is a large-scale language model (LLM)-based chatbot system in the education domain. Its goal is to support personalized, fair, and compassionate intelligent education, serving teachers, students, and parents. Guided by theories from psychology and education, it further strengthens educational functions such as open question answering, essay assessment, Socratic teaching, and emotional support based on the existing basic LLMs. Particularly, we learn domain-specific knowledge by pre-training on the educational corpus and stimulate various skills with tool use by fine-tuning on designed system prompts and instructions. Currently, EduChat is available online as an open-source project, with its code, data, and model parameters available on platforms (e.g., GitHub https://github.com/icalk-nlp/EduChat, Hugging Face https://huggingface.co/ecnu-icalk ). We also prepare a demonstration of its capabilities online (https://vimeo.com/851004454). This initiative aims to promote research and applications of LLMs for intelligent education.

Qi'ao Xu, Tianwen Qian, Yuqian Fu et al.

A core capability towards general embodied intelligence lies in localizing task-relevant objects from an egocentric perspective, formulated as Spatio-Temporal Video Grounding (STVG). Despite recent progress, existing STVG studies remain largely confined to object-centric and descriptive instructions, neglecting the task-oriented reasoning that is crucial for embodied agents to accomplish goal-directed interactions. To bridge this gap, we introduce \textbf{ToG-Bench}, the first task-oriented spatio-temporal video grounding benchmark for egocentric videos. ToG-Bench is characterized by three key features: (1) \textbf{Task-oriented Grounding}, which requires identifying and localizing objects based on intended tasks rather than straightforward descriptions; (2) \textbf{Explicit-Implicit Dual Grounding}, where target objects can be either explicitly mentioned or implicitly inferred by contextual reasoning; (3) \textbf{One-to-Many Grounding}, where a single instruction may correspond to multiple objects involved in task execution. Built upon videos sourced from ScanNet, ToG-Bench comprises 100 annotated clips with 2,704 task-oriented grounding instructions, constructed via a semi-automated pipeline that combines foundation model annotation and human refinement. In addition, we introduce a set of task-level evaluation metrics tailored for multi-object and explicit-implicit object grounding, and systematically benchmark seven state-of-the-art MLLMs. Extensive experiments reveal the intrinsic challenges of task-oriented STVG and substantial performance gaps across explicit-implicit and multi-object grounding, highlighting the difficulty of bridging perception and interaction in embodied scenarios. Data and code will be released at: \href{https://github.com/qaxuDev/ToG-Bench}{https://github.com/qaxuDev/ToG-Bench}..

Ying Hu, Yuwu Tang, Hao Huang et al.

Speech emotion recognition (SER) is an essential part of human-computer interaction. In this paper, we propose an SER network based on a Graph Isomorphism Network with Weighted Multiple Aggregators (WMA-GIN), which can effectively handle the problem of information confusion when neighbour nodes' features are aggregated together in GIN structure. Moreover, a Full-Adjacent (FA) layer is adopted for alleviating the over-squashing problem, which is existed in all Graph Neural Network (GNN) structures, including GIN. Furthermore, a multi-phase attention mechanism and multi-loss training strategy are employed to avoid missing the useful emotional information in the stacked WMA-GIN layers. We evaluated the performance of our proposed WMA-GIN on the popular IEMOCAP dataset. The experimental results show that WMA-GIN outperforms other GNN-based methods and is comparable to some advanced non-graph-based methods by achieving 72.48% of weighted accuracy (WA) and 67.72% of unweighted accuracy (UA).

Shun Huang, Zhihua Fang, Liang He

Unsupervised anomalous sound detection aims to detect unknown anomalous sounds by training a model using only normal audio data. Despite advancements in self-supervised methods, the issue of frequent false alarms when handling samples of the same type from different machines remains unresolved. This paper introduces a novel training technique called one-stage supervised contrastive learning (OS-SCL), which significantly addresses this problem by perturbing features in the embedding space and employing a one-stage noisy supervised contrastive learning approach. On the DCASE 2020 Challenge Task 2, it achieved 94.64\% AUC, 88.42\% pAUC, and 89.24\% mAUC using only Log-Mel features. Additionally, a time-frequency feature named TFgram is proposed, which is extracted from raw audio. This feature effectively captures critical information for anomalous sound detection, ultimately achieving 95.71\% AUC, 90.23\% pAUC, and 91.23\% mAUC. The source code is available at: \underline{www.github.com/huangswt/OS-SCL}.

Kunting Li, Yong Hu, Liang He et al.

Chinese Spell Checking (CSC) aims to detect and correct spelling errors in sentences. Despite Large Language Models (LLMs) exhibit robust capabilities and are widely applied in various tasks, their performance on CSC is often unsatisfactory. We find that LLMs fail to meet the Chinese character-level constraints of the CSC task, namely equal length and phonetic similarity, leading to a performance bottleneck. Further analysis reveal that this issue stems from the granularity of tokenization, as current mixed character-word tokenization struggles to satisfy these character-level constraints. To address this issue, we propose C-LLM, a Large Language Model-based Chinese Spell Checking method that learns to check errors Character by Character. Character-level tokenization enables the model to learn character-level alignment, effectively mitigating issues related to character-level constraints. Furthermore, CSC is simplified to replication-dominated and substitution-supplemented tasks. Experiments on two CSC benchmarks demonstrate that C-LLM achieves an average improvement of 10% over existing methods. Specifically, it shows a 2.1% improvement in general scenarios and a significant 12% improvement in vertical domain scenarios, establishing state-of-the-art performance. The source code can be accessed at https://github.com/ktlKTL/C-LLM.

Kedi Chen, Dezhao Ruan, Yuhao Dan et al.

Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamental types, which is characterized by its particular-to-general thinking process and the non-uniqueness of its answers. The inductive mode is crucial for knowledge generalization and aligns better with human cognition, so it is a fundamental mode of learning, hence attracting increasing interest. Despite the importance of inductive reasoning, there is no systematic summary of it. Therefore, this paper presents the first comprehensive survey of inductive reasoning for LLMs. First, methods for improving inductive reasoning are categorized into three main areas: post-training, test-time scaling, and data augmentation. Then, current benchmarks of inductive reasoning are summarized, and a unified sandbox-based evaluation approach with the observation coverage metric is derived. Finally, we offer some analyses regarding the source of inductive ability and how simple model architectures and data help with inductive tasks, providing a solid foundation for future research.

Xin Yi, Linlin Wang, Xiaoling Wang et al.

Impressive results have been achieved in natural language processing (NLP) tasks through the training of large language models (LLMs). However, these models occasionally produce toxic content such as insults, threats, and profanity in response to certain prompts, thereby constraining their practical utility. To tackle this issue, various finetuning-based and decoding-based approaches have been utilized to mitigate toxicity. However, these methods typically necessitate additional costs such as high-quality training data or auxiliary models. In this paper, we propose fine-grained detoxification via instance-level prefixes (FGDILP) to mitigate toxic text without additional cost. Specifically, FGDILP contrasts the contextualized representation in attention space using a positive prefix-prepended prompt against multiple negative prefix-prepended prompts at the instance level. This allows for constructing fine-grained subtoxicity vectors, which enables collaborative detoxification by fusing them to correct the normal generation process when provided with a raw prompt. We validate that FGDILP enables controlled text generation with regard to toxicity at both the utterance and context levels. Our method surpasses prompt-based baselines in detoxification, although at a slight cost to generation fluency and diversity.

Wenhao Ding, Liang He

The goal of acoustic (or sound) events detection (AED or SED) is to predict the temporal position of target events in given audio segments. This task plays a significant role in safety monitoring, acoustic early warning and other scenarios. However, the deficiency of data and diversity of acoustic event sources make the AED task a tough issue, especially for prevalent data-driven methods. In this paper, we start by analyzing acoustic events according to their time-frequency domain properties, showing that different acoustic events have different time-frequency scale characteristics. Inspired by the analysis, we propose an adaptive multi-scale detection (AdaMD) method. By taking advantage of the hourglass neural network and gated recurrent unit (GRU) module, our AdaMD produces multiple predictions at different temporal and frequency resolutions. An adaptive training algorithm is subsequently adopted to combine multi-scale predictions to enhance its overall capability. Experimental results on Detection and Classification of Acoustic Scenes and Events 2017 (DCASE 2017) Task 2, DCASE 2016 Task 3 and DCASE 2017 Task 3 demonstrate that the AdaMD outperforms published state-of-the-art competitors in terms of the metrics of event error rate (ER) and F1-score. The verification experiment on our collected factory mechanical dataset also proves the noise-resistant capability of the AdaMD, providing the possibility for it to be deployed in the complex environment.

Yi Liu, Liang He, Jia Liu

In neural network based speaker verification, speaker embedding is expected to be discriminative between speakers while the intra-speaker distance should remain small. A variety of loss functions have been proposed to achieve this goal. In this paper, we investigate the large margin softmax loss with different configurations in speaker verification. Ring loss and minimum hyperspherical energy criterion are introduced to further improve the performance. Results on VoxCeleb show that our best system outperforms the baseline approach by 15\% in EER, and by 13\%, 33\% in minDCF08 and minDCF10, respectively.

Jingyang Zhang, Wenhao Ding, Jintao Kang et al.

Most attention-based methods only concentrate along the time axis, which is insufficient for Acoustic Event Detection (AED). Meanwhile, previous methods for AED rarely considered that target events possess distinct temporal and frequential scales. In this work, we propose a Multi-Scale Time-Frequency Attention (MTFA) module for AED. MTFA gathers information at multiple resolutions to generate a time-frequency attention mask which tells the model where to focus along both time and frequency axis. With MTFA, the model could capture the characteristics of target events with different scales. We demonstrate the proposed method on Task 2 of Detection and Classification of Acoustic Scenes and Events (DCASE) 2017 Challenge. Our method achieves competitive results on both development dataset and evaluation dataset.

Liang He, Xianhong Chen, Can Xu et al.

Most current state-of-the-art text-independent speaker verification systems take probabilistic linear discriminant analysis (PLDA) as their backend classifiers. The parameters of PLDA are often estimated by maximizing the objective function, which focuses on increasing the value of log-likelihood function, but ignoring the distinction between speakers. In order to better distinguish speakers, we propose a multi-objective optimization training for PLDA. Experiment results show that the proposed method has more than 10% relative performance improvement in both EER and MinDCF on the NIST SRE14 i-vector challenge dataset, and about 20% relative performance improvement in EER on the MCE18 dataset.

Yi Liu, Liang He, Weiwei Liu et al.

The pooling layer is an essential component in the neural network based speaker verification. Most of the current networks in speaker verification use average pooling to derive the utterance-level speaker representations. Average pooling takes every frame as equally important, which is suboptimal since the speaker-discriminant power is different between speech segments. In this paper, we present a unified attention-based pooling framework and combine it with the multi-head attention. Experiments on the Fisher and NIST SRE 2010 dataset show that involving outputs from lower layers to compute the attention weights can outperform average pooling and achieve better results than vanilla attention method. The multi-head attention further improves the performance.

Yi Liu, Liang He, Jia Liu et al.

Speaker embeddings achieve promising results on many speaker verification tasks. Phonetic information, as an important component of speech, is rarely considered in the extraction of speaker embeddings. In this paper, we introduce phonetic information to the speaker embedding extraction based on the x-vector architecture. Two methods using phonetic vectors and multi-task learning are proposed. On the Fisher dataset, our best system outperforms the original x-vector approach by 20% in EER, and by 15%, 15% in minDCF08 and minDCF10, respectively. Experiments conducted on NIST SRE10 further demonstrate the effectiveness of the proposed methods.

Wenhao Ding, Liang He

In this paper, we propose an enhanced triplet method that improves the encoding process of embeddings by jointly utilizing generative adversarial mechanism and multitasking optimization. We extend our triplet encoder with Generative Adversarial Networks (GANs) and softmax loss function. GAN is introduced for increasing the generality and diversity of samples, while softmax is for reinforcing features about speakers. For simplification, we term our method Multitasking Triplet Generative Adversarial Networks (MTGAN). Experiment on short utterances demonstrates that MTGAN reduces the verification equal error rate (EER) by 67% (relatively) and 32% (relatively) over conventional i-vector method and state-of-the-art triplet loss method respectively. This effectively indicates that MTGAN outperforms triplet methods in the aspect of expressing the high-level feature of speaker information.

Yi Liu, Liang He, Weiqiang Zhang et al.

Frame alignments can be computed by different methods in GMM-based speaker verification. By incorporating a phonetic Gaussian mixture model (PGMM), we are able to compare the performance using alignments extracted from the deep neural networks (DNN) and the conventional hidden Markov model (HMM) in digit-prompted speaker verification. Based on the different characteristics of these two alignments, we present a novel content verification method to improve the system security without much computational overhead. Our experiments on the RSR2015 Part-3 digit-prompted task show that, the DNN based alignment performs on par with the HMM alignment. The results also demonstrate the effectiveness of the proposed Kullback-Leibler (KL) divergence based scoring to reject speech with incorrect pass-phrases.

Yi Liu, Liang He, Yao Tian et al.

Text-dependent speaker verification is becoming popular in the speaker recognition society. However, the conventional i-vector framework which has been successful for speaker identification and other similar tasks works relatively poorly in this task. Researchers have proposed several new methods to improve performance, but it is still unclear that which model is the best choice, especially when the pass-phrases are prompted during enrollment and test. In this paper, we introduce four modeling methods and compare their performance on the newly published RedDots dataset. To further explore the influence of different frame alignments, Viterbi and forward-backward algorithms are both used in the HMM-based models. Several bottleneck features are also investigated. Our experiments show that, by explicitly modeling the lexical content, the HMM-based modeling achieves good results in the fixed-phrase condition. In the prompted-phrase condition, GMM-HMM and i-vector/HMM are not as successful. In both conditions, the forward-backward algorithm brings more benefits to the i-vector/HMM system. Additionally, we also find that even though bottleneck features perform well for text-independent speaker verification, they do not outperform MFCCs on the most challenging Imposter-Correct trials on RedDots.