arXiv subjects

Ya Li

Publications and source records attributed to Ya Li.

At least 55 records · Page 3Linked to original sources

arXiv2025

MGFF-TDNN: A Multi-Granularity Feature Fusion TDNN Model with Depth-Wise Separable Module for Speaker Verification

In speaker verification, traditional models often emphasize modeling long-term contextual features to capture global speaker characteristics. However, this approach can neglect fine-grained voiceprint information, which contains highly discriminative features essential for robust speaker embeddings. This paper introduces a novel model architecture, termed MGFF-TDNN, based on multi-granularity feature fusion. The MGFF-TDNN leverages a two-dimensional depth-wise separable convolution module, enhanced with local feature modeling, as a front-end feature extractor to effectively capture time-frequency domain features. To achieve comprehensive multi-granularity feature fusion, we propose the M-TDNN structure, which integrates global contextual modeling with fine-grained feature extraction by combining time-delay neural networks and phoneme-level feature pooling. Experiments on the VoxCeleb dataset demonstrate that the MGFF-TDNN achieves outstanding performance in speaker verification while remaining efficient in terms of parameters and computational resources.

cs.SD↗

arXiv2025

MER 2025: When Affective Computing Meets Large Language Models

MER2025 is the third year of our MER series of challenges, aiming to bring together researchers in the affective computing community to explore emerging trends and future directions in the field. Previously, MER2023 focused on multi-label learning, noise robustness, and semi-supervised learning, while MER2024 introduced a new track dedicated to open-vocabulary emotion recognition. This year, MER2025 centers on the theme "When Affective Computing Meets Large Language Models (LLMs)".We aim to shift the paradigm from traditional categorical frameworks reliant on predefined emotion taxonomies to LLM-driven generative methods, offering innovative solutions for more accurate and reliable emotion understanding. The challenge features four tracks: MER-SEMI focuses on fixed categorical emotion recognition enhanced by semi-supervised learning; MER-FG explores fine-grained emotions, expanding recognition from basic to nuanced emotional states; MER-DES incorporates multimodal cues (beyond emotion words) into predictions to enhance model interpretability; MER-PR investigates whether emotion prediction results can improve personality recognition performance. For the first three tracks, baseline code is available at MERTools, and datasets can be accessed via Hugging Face. For the last track, the dataset and baseline code are available on GitHub.

cs.HC↗

arXiv2025

Improved global determination of two-meson distribution amplitudes from multi-body $B$ decays

We improve the perturbative QCD (PQCD) formalism for multi-body charmless hadronic $B$ meson decays, such as $B\to VP_3\to P_1P_2P_3$, by resolving the possible discrepancy in parametrizing the contribution of the $P$-wave resonance $V$ to the two-meson distribution amplitudes (DAs) associated with the pairs $P_1P_2=ππ, Kπ, KK$. The determination of the Gegenbauer moments in the two-meson DAs is then updated in the global fit of the improved PQCD factorization formulas at leading order in the strong coupling $α_s$ to available data for branching ratios and polarization fractions of three- and four-body $B$ decays. The convergence of the Gegenbauer expansion of the resultant two-meson DAs is manifest. The satisfactory quality of the fit implies the consistency of the PQCD framework for multi-body $B$ decays and the universality of the nonperturbative two-meson DAs. In particular, the predicted longitudinal polarization fraction $f_0(B_s^0\to K^{*0} {\bar K}^{*0})=28.2^{+8.8}_{-9.5} \%$ with the updated Gegenbauer moments matches well the measurement. The observable $L_{K^{*0}{\bar K}^{*0}}=7.7^{+4.9}_{-3.8}$, defined as the ratio of the longitudinal amplitudes of the two $U$-spin related channels $B_s^0\to K^{*0} {\bar K}^{*0}$ and $B^0\to K^{*0} {\bar K}^{*0}$, accommodates the current data within errors. It is found that the direct $CP$ asymmetries ${\cal A}^{0,||,\bot}_{\rm CP}$ in the polarization states of some four-body decays $B\to V_1V_2\to (P_1P_2)(P_3P_4)$ might be large, but the destruction among them result in small net $CP$ violation. Our predictions can be confronted with LHCb and Belle-II data in the future.

hep-ph↗

arXiv2025

CP violation analysis of $D^0\to M^0 K \to M^0(π^\pm \ell^\mp ν)$

CP violation in the charm sector is highly sensitive to new physics due to its small predicted value within the standard model. By this work, we investigated the CP violation in the cascade decay process $D^0(t_1) \to π^0 K(t_2) \to π^0(π^\pm \ell^\mp ν)$. Our results indicate that the CP violation induced by the interference of unmixed $D$-meson decay amplitudes dominates, with a peak value reaching $5 \times 10^{-3}$. This is one order of magnitude larger than the sub-leading contribution, namely the double-mixing CP violation. Furthermore, the CP violation in the decay channel with the semileptonic final state $π^- \ell^+ ν_\ell$ is one to two orders of magnitude larger than that in the channel with $ π^+ \ell^- \barν_\ell$. We propose that the CP asymmetry of the combined two decay channels can be measured experimentally. The resulting value is approximately half of the CP violation observed in the $π^- \ell^+ ν_\ell$ channel, with the dominant contribution still reaching the order of $10^{-3}$. This approach offers the advantage of eliminating the need for flavor tagging of the initial $D$ meson, thereby avoiding associated efficiency losses.

hep-ph↗

arXiv2025

Psy-Insight: Explainable Multi-turn Bilingual Dataset for Mental Health Counseling

The in-context learning capabilities of large language models (LLMs) show great potential in mental health support. However, the lack of counseling datasets, particularly in Chinese corpora, restricts their application in this field. To address this, we constructed Psy-Insight, the first mental health-oriented explainable multi-task bilingual dataset. We collected face-to-face multi-turn counseling dialogues, which are annotated with multi-task labels and conversation process explanations. Our annotations include psychotherapy, emotion, strategy, and topic labels, as well as turn-level reasoning and session-level guidance. Psy-Insight is not only suitable for tasks such as label recognition but also meets the need for training LLMs to act as empathetic counselors through logical reasoning. Experiments show that training LLMs on Psy-Insight enables the models to not only mimic the conversation style but also understand the underlying strategies and reasoning of counseling.

cs.CL↗

arXiv2025

Psy-Copilot: Visual Chain of Thought for Counseling

Large language models (LLMs) are becoming increasingly popular in the field of psychological counseling. However, when human therapists work with LLMs in therapy sessions, it is hard to understand how the model gives the answers. To address this, we have constructed Psy-COT, a graph designed to visualize the thought processes of LLMs during therapy sessions. The Psy-COT graph presents semi-structured counseling conversations alongside step-by-step annotations that capture the reasoning and insights of therapists. Moreover, we have developed Psy-Copilot, which is a conversational AI assistant designed to assist human psychological therapists in their consultations. It can offer traceable psycho-information based on retrieval, including response candidates, similar dialogue sessions, related strategies, and visual traces of results. We have also built an interactive platform for AI-assisted counseling. It has an interface that displays the relevant parts of the retrieval sub-graph. The Psy-Copilot is designed not to replace psychotherapists but to foster collaboration between AI and human therapists, thereby promoting mental health development. Our code and demo are both open-sourced and available for use.

cs.CL↗

arXiv2025

Next-to-leading-order time-like rho electromagnetic form factors in ${k_{\rm T}}$ factorization

We calculate the time-like $ρ$ electromagnetic (EM) form factor in the $k_T$ factorization formalism by including the next-to-leading-order (NLO) corrections of the leading-twist and sub-leading twist contributions. It's observed that the NLO correction to the magnitude of the LO leading-twist form factor is lower than $30\%$ at large invariant mass squared $Q^2 > 30 \text{GeV}^2$. It is found that the $ρ$ meson EM form factor is dominated by twist-3 contribution instead of by twist-2 one because of the end-point enhancement. The theoretical predictions of the moduli of three helicity amplitudes and total cross section are analyzed at $\sqrt{s}=10.58$ GeV, which are consistent with measurements from BABAR Collaboration.

hep-ph↗

arXiv2024

Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation

Text-to-audio (TTA) model is capable of generating diverse audio from textual prompts. However, most mainstream TTA models, which predominantly rely on Mel-spectrograms, still face challenges in producing audio with rich content. The intricate details and texture required in Mel-spectrograms for such audio often surpass the models' capacity, leading to outputs that are blurred or lack coherence. In this paper, we begin by investigating the critical role of U-Net in Mel-spectrogram generation. Our analysis shows that in U-Net structure, high-frequency components in skip-connections and the backbone influence texture and detail, while low-frequency components in the backbone are critical for the diffusion denoising process. We further propose ``Mel-Refine'', a plug-and-play approach that enhances Mel-spectrogram texture and detail by adjusting different component weights during inference. Our method requires no additional training or fine-tuning and is fully compatible with any diffusion-based TTA architecture. Experimental results show that our approach boosts performance metrics of the latest TTA model Tango2 by 25\%, demonstrating its effectiveness.

cs.SD↗

arXiv2024

Perceptual learning in contour detection transfer across changes in contour path and orientation

The integration of local elements into shape contours is critical for target detection and identification in cluttered scenes. Previous studies have shown that observers can learn to use image regularities for contour integration and target identification. However, we still know little about the generalization of perceptual learning in contour integration. Specifically, whether training in contour detection task could transfer to untrained contour type, path or orientation is still unclear. In a series of four experiments, human perceptual learning in contour detection was studied using psychophysical methods. We trained participants to detect contours in cluttered scenes over several days, which resulted in a significant improvement in sensitivity to trained contour type. This improved sensitivity was highly specific to contour type, but transfer across changes in contour path and contour orientation. These results suggest that short-term training improves the ability to integrate specific types of contours by optimizing the ability of the visual system to extract specific image regularities. The differential specificity and generalization across different stimulus features may support the involvement of both low-level and higher-level visual areas in perceptual learning in contour detection. These findings provide further insights into understanding the nature and the brain plasticity mechanism of contour integration learning.

q-bio.NC↗

arXiv2024

Enhancing Modal Fusion by Alignment and Label Matching for Multimodal Emotion Recognition

To address the limitation in multimodal emotion recognition (MER) performance arising from inter-modal information fusion, we propose a novel MER framework based on multitask learning where fusion occurs after alignment, called Foal-Net. The framework is designed to enhance the effectiveness of modality fusion and includes two auxiliary tasks: audio-video emotion alignment (AVEL) and cross-modal emotion label matching (MEM). First, AVEL achieves alignment of emotional information in audio-video representations through contrastive learning. Then, a modal fusion network integrates the aligned features. Meanwhile, MEM assesses whether the emotions of the current sample pair are the same, providing assistance for modal information fusion and guiding the model to focus more on emotional information. The experimental results conducted on IEMOCAP corpus show that Foal-Net outperforms the state-of-the-art methods and emotion alignment is necessary before modal fusion.

cs.MM↗

arXiv2024

ICAGC 2024: Inspirational and Convincing Audio Generation Challenge 2024

The Inspirational and Convincing Audio Generation Challenge 2024 (ICAGC 2024) is part of the ISCSLP 2024 Competitions and Challenges track. While current text-to-speech (TTS) technology can generate high-quality audio, its ability to convey complex emotions and controlled detail content remains limited. This constraint leads to a discrepancy between the generated audio and human subjective perception in practical applications like companion robots for children and marketing bots. The core issue lies in the inconsistency between high-quality audio generation and the ultimate human subjective experience. Therefore, this challenge aims to enhance the persuasiveness and acceptability of synthesized audio, focusing on human alignment convincing and inspirational audio generation. A total of 19 teams have registered for the challenge, and the results of the competition and the competition are described in this paper.

eess.AS↗

arXiv2024

SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversion

Diffusion-based singing voice conversion (SVC) models have shown better synthesis quality compared to traditional methods. However, in cross-domain SVC scenarios, where there is a significant disparity in pitch between the source and target voice domains, the models tend to generate audios with hoarseness, posing challenges in achieving high-quality vocal outputs. Therefore, in this paper, we propose a Self-supervised Pitch Augmentation method for Singing Voice Conversion (SPA-SVC), which can enhance the voice quality in SVC tasks without requiring additional data or increasing model parameters. We innovatively introduce a cycle pitch shifting training strategy and Structural Similarity Index (SSIM) loss into our SVC model, effectively enhancing its performance. Experimental results on the public singing datasets M4Singer indicate that our proposed method significantly improves model performance in both general SVC scenarios and particularly in cross-domain SVC scenarios.

cs.SD↗

arXiv2024

Near-Field Channel Estimation for Extremely Large-Scale Terahertz Communications

Future Terahertz communications exhibit significant potential in accommodating ultra-high-rate services. Employing extremely large-scale array antennas is a key approach to realize this potential, as they can harness substantial beamforming gains to overcome the severe path loss and leverage the electromagnetic advantages in the near field. This paper proposes novel estimation methods designed to enhance efficiency in Terahertz widely-spaced multi-subarray (WSMS) systems. Initially, we introduce three sparse channel representation methods: polar-domain representation (PD-R), multi-angular-domain representation (MAD-R), and two-dimensional polar-angular-domain representation (2D-PAD-R). Each method is meticulously developed for near-field WSMS channels, capitalizing on their sparsity characteristics. Building on this, we propose four estimation frameworks using the sparse recovery theory: polar-domain estimation (PD-E), multi-angular-domain estimation (MAD-E), two-stage polar-angular-domain estimation (TS-PAD-E), and two-dimensional polar-angular-domain estimation (2D-PAD-E). Particularly, 2D-PAD-E, integrating a 2D dictionary process, and TS-PAD-E, with its sequential approach to angle and distance estimation, stand out as particularly effective for near-field angle-distance estimation, enabling decoupled calculation of these parameters. Overall, these frameworks provide versatile and efficient solutions for WSMS channel estimation, balancing low complexity with high-performance outcomes. Additionally, they represent a fresh perspective on near-field signal processing.

eess.SP↗

arXiv2024

Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model

Recent advances in large language models (LLMs) and development of audio codecs greatly propel the zero-shot TTS. They can synthesize personalized speech with only a 3-second speech of an unseen speaker as acoustic prompt. However, they only support short speech prompts and cannot leverage longer context information, as required in audiobook and conversational TTS scenarios. In this paper, we introduce a novel audio codec-based TTS model to adapt context features with multiple enhancements. Inspired by the success of Qformer, we propose a multi-modal context-enhanced Qformer (MMCE-Qformer) to utilize additional multi-modal context information. Besides, we adapt a pretrained LLM to leverage its understanding ability to predict semantic tokens, and use a SoundStorm to generate acoustic tokens thereby enhancing audio quality and speaker similarity. The extensive objective and subjective evaluations show that our proposed method outperforms baselines across various context TTS scenarios.

cs.SD↗

arXiv2024

Retrieval Augmented Generation in Prompt-based Text-to-Speech Synthesis with Context-Aware Contrastive Language-Audio Pretraining

Recent prompt-based text-to-speech (TTS) models can clone an unseen speaker using only a short speech prompt. They leverage a strong in-context ability to mimic the speech prompts, including speaker style, prosody, and emotion. Therefore, the selection of a speech prompt greatly influences the generated speech, akin to the importance of a prompt in large language models (LLMs). However, current prompt-based TTS models choose the speech prompt manually or simply at random. Hence, in this paper, we adapt retrieval augmented generation (RAG) from LLMs to prompt-based TTS. Unlike traditional RAG methods, we additionally consider contextual information during the retrieval process and present a Context-Aware Contrastive Language-Audio Pre-training (CA-CLAP) model to extract context-aware, style-related features. The objective and subjective evaluations demonstrate that our proposed RAG method outperforms baselines, and our CA-CLAP achieves better results than text-only retrieval methods.

cs.SD↗

arXiv2024

Explainable Multimodal Emotion Recognition

Multimodal emotion recognition is an important research topic in artificial intelligence, whose main goal is to integrate multimodal clues to identify human emotional states. Current works generally assume accurate labels for benchmark datasets and focus on developing more effective architectures. However, emotion annotation relies on subjective judgment. To obtain more reliable labels, existing datasets usually restrict the label space to some basic categories, then hire plenty of annotators and use majority voting to select the most likely label. However, this process may result in some correct but non-candidate or non-majority labels being ignored. To ensure reliability without ignoring subtle emotions, we propose a new task called ``Explainable Multimodal Emotion Recognition (EMER)''. Unlike traditional emotion recognition, EMER takes a step further by providing explanations for these predictions. Through this task, we can extract relatively reliable labels since each label has a certain basis. Meanwhile, we borrow large language models (LLMs) to disambiguate unimodal clues and generate more complete multimodal explanations. From them, we can extract richer emotions in an open-vocabulary manner. This paper presents our initial attempt at this task, including introducing a new dataset, establishing baselines, and defining evaluation metrics. In addition, EMER can serve as a benchmark task to evaluate the audio-video-text understanding performance of multimodal LLMs.

cs.MM↗

arXiv2024

Mutual Information-Based Integrated Sensing and Communications: A WMMSE Framework

In this letter, a weighted minimum mean square error (WMMSE) empowered integrated sensing and communication (ISAC) system is investigated. One transmitting base station and one receiving wireless access point are considered to serve multiple users a sensing target. Based on the theory of mutual-information (MI), communication MI and sensing MI rate are utilized as the performance metrics under the presence of clutters. In particular, we propose an novel MI-based WMMSE-ISAC method by developing a unique transceiver design mechanism to maximize the weighted sensing and communication sum-rate of this system. Such a maximization process is achieved by utilizing the classical method -- WMMSE, aiming to better manage the effect of sensing clutters and the interference among users. Numerical results show the effectiveness of our proposed method, and the performance trade-off between sensing and communication is also validated.

eess.SP↗

arXiv2024

Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation

Recent advancements in diffusion models and large language models (LLMs) have significantly propelled the field of AIGC. Text-to-Audio (TTA), a burgeoning AIGC application designed to generate audio from natural language prompts, is attracting increasing attention. However, existing TTA studies often struggle with generation quality and text-audio alignment, especially for complex textual inputs. Drawing inspiration from state-of-the-art Text-to-Image (T2I) diffusion models, we introduce Auffusion, a TTA system adapting T2I model frameworks to TTA task, by effectively leveraging their inherent generative strengths and precise cross-modal alignment. Our objective and subjective evaluations demonstrate that Auffusion surpasses previous TTA approaches using limited data and computational resource. Furthermore, previous studies in T2I recognizes the significant impact of encoder choice on cross-modal alignment, like fine-grained details and object bindings, while similar evaluation is lacking in prior TTA works. Through comprehensive ablation studies and innovative cross-attention map visualizations, we provide insightful assessments of text-audio alignment in TTA. Our findings reveal Auffusion's superior capability in generating audios that accurately match textual descriptions, which further demonstrated in several related tasks, such as audio style transfer, inpainting and other manipulations. Our implementation and demos are available at https://auffusion.github.io.

cs.SD↗