arXiv subjects

Zhiqi Ai

Publications and source records attributed to Zhiqi Ai.

11 recordsLinked to original sources

arXiv2026

DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detection

Stereo-based 3D obstacle perception for autonomous driving is currently constrained by an imbalanced triplet: deployment cost, detection accuracy, and open-set adaptability. While existing methods struggle to balance these three competing objectives, there is an urgent demand for high-precision, real-time algorithms capable of detecting arbitrary obstacles in the wild. In this paper, we present DDStereo, a novel Dual-Decoder Stereo Transformer that achieves a synergistic integration of 3D object detection and Out-of-Distribution (OoD) road anomaly detection. Leveraging the geometric priors of stereo disparity, our approach effectively couples 3D attribute regression with open-set foreground detection within a streamlined dual-branch decoder architecture. Conventional methods rely on complex feature-level fusion; DDStereo maintains execution efficiency by employing a decoupled decoding strategy and shared object-level queries to ensure cross-modal target alignment. Extensive evaluations of public benchmarks demonstrate that DDStereo not only achieves state-of-the-art accuracy under open-set and closed-set protocols. Our method delivers real-time performance comparable to monocular 3D detection baselines, providing a cost-effective solution for the perception of obstacles of the normal and OoD category. Code and models are available at https://github.com/shiyi-mu/DDStereo.

cs.CV↗

arXiv2026

Stabilizing Short Duration Speaker Verification through Neural Re-scoring with Hybrid Enrollment

Short-duration speaker verification (SDSV) is crucial for personalized keyword spotting, where test utterances are typically shorter than three seconds. Limited speech duration results in unstable speaker representations and increased sensitivity to noise and phoneme variations, thereby degrading performance. To investigate this issue, we construct VoxPhrase, a large-scale SDSV corpus automatically segmented from the VoxCeleb dataset. Our analysis shows that text-dependent (TD) enrollment is constrained by duration and yields unstable speaker representations. In contrast, although text-independent (TI) enrollment introduces content mismatch, its representations become more stable as the enrollment duration increases. Accordingly, we propose a hybrid-enrollment neural re-scoring framework that combines TD and TI enrollment and performs frame-level comparison via parallel cross-attention. Experiments on VoxPhrase demonstrate consistent improvements across multiple speaker models.

eess.AS↗

arXiv2026

Effective User-defined Keyword Spotting with Dual-stage Matching, Multi-modal Enrollment, and Continual Adaptation

User-defined keyword spotting (KWS) is crucial for personalized voice interaction, yet existing methods face several challenges: (1) insufficient discriminability among confusable words, (2) performance inconsistency across speakers with varying pronunciations, and (3) high data cost to ensure reliable wake-word performance. In this paper, we introduce DMA-KWS, an efficient and robust framework for user-defined keyword spotting. First, it adopts a dual-stage matching pipeline: CTC decoding with streaming phoneme search to locate candidate segments, followed by QbyT with a phoneme matcher for fine-grained verification, enabling it to better distinguish confusable words. Next, multi-modal enrollment fuses user-specific speech with text embeddings to further improve accuracy for registered users. Finally, a parameter-efficient continual adaptation mechanism performs lightweight updates using synthetic and real data. Extensive experiments demonstrate the superior performance of DMA-KWS. On the LibriPhrase Hard subset, it achieves 97.85% AUC and 6.13% EER, reaching state-of-the-art performance. In speaker-dependent settings, DMA-KWS consistently outperforms text-only enrollment, demonstrating significant performance gains. Moreover, the proposed parameter-efficient fine-tuning mechanism adapts DMA-KWS with only 187k updated parameters, further enhancing KWS performance while ensuring suitability for on-device deployment.

eess.AS↗

arXiv2025

StereoDETR: Stereo-based Transformer for 3D Object Detection

Compared to monocular 3D object detection, stereo-based 3D methods offer significantly higher accuracy but still suffer from high computational overhead and latency. The state-of-the-art stereo 3D detection method achieves twice the accuracy of monocular approaches, yet its inference speed is only half as fast. In this paper, we propose StereoDETR, an efficient stereo 3D object detection framework based on DETR. StereoDETR consists of two branches: a monocular DETR branch and a stereo branch. The DETR branch is built upon 2D DETR with additional channels for predicting object scale, orientation, and sampling points. The stereo branch leverages low-cost multi-scale disparity features to predict object-level depth maps. These two branches are coupled solely through a differentiable depth sampling strategy. To handle occlusion, we introduce a constrained supervision strategy for sampling points without requiring extra annotations. StereoDETR achieves real-time inference and is the first stereo-based method to surpass monocular approaches in speed. It also achieves competitive accuracy on the public KITTI benchmark, setting new state-of-the-art results on pedestrian and cyclist subsets. The code is available at https://github.com/shiyi-mu/StereoDETR-OPEN.

cs.CV↗

arXiv2025

Dual Data Scaling for Robust Two-Stage User-Defined Keyword Spotting

In this paper, we propose DS-KWS, a two-stage framework for robust user-defined keyword spotting. It combines a CTC-based method with a streaming phoneme search module to locate candidate segments, followed by a QbyT-based method with a phoneme matcher module for verification at both the phoneme and utterance levels. To further improve performance, we introduce a dual data scaling strategy: (1) expanding the ASR corpus from 460 to 1,460 hours to strengthen the acoustic model; and (2) leveraging over 155k anchor classes to train the phoneme matcher, significantly enhancing the distinction of confusable words. Experiments on LibriPhrase show that DS-KWS significantly outperforms existing methods, achieving 6.13\% EER and 97.85\% AUC on the Hard subset. On Hey-Snips, it achieves zero-shot performance comparable to full-shot trained models, reaching 99.13\% recall at one false alarm per hour.

cs.SD↗

arXiv2025

Enhanced Fingerprint-based Positioning With Practical Imperfections: Deep learning-based approaches

High-precision positioning is vital for cellular networks to support innovative applications such as extended reality, unmanned aerial vehicles (UAVs), and industrial Internet of Things (IoT) systems. Existing positioning algorithms using deep learning techniques require vast amounts of labeled data, which are difficult to obtain in real-world cellular environments, and these models often struggle to generalize effectively. To advance cellular positioning techniques, the 2024 Wireless Communication Algorithm Elite Competition as conducted, which provided a dataset from a three-sector outdoor cellular system, incorporating practical challenges such as limited labeled-dataset, dynamic wireless environments within the target and unevenly-spaced anchors, Our team developed three innovative positioning frameworks that swept the top three awards of this competition, namely the semi-supervised framework with consistency, ensemble learning-based algorithm and decoupled mapping heads-based algorithm. Specifically, the semi-supervised framework with consistency effectively generates high-quality pseudo-labels, enlarging the labeled-dataset for model training. The ensemble learning-based algorithm amalgamates the positioning coordinates from models trained under different strategies, effectively combating the dynamic positioning environments. The decoupled mapping heads-based algorithm utilized sector rotation scheme to resolve the uneven-spaced anchor issue. Simulation results demonstrate the superior performance of our proposed positioning algorithms compared to existing benchmarks in terms of the {90%, 80%, 67%, 50%} percentile and mean distance error.

eess.SP↗

arXiv2025

Stage-wise Adaptive Label Distribution for Facial Age Estimation

Label ambiguity poses a significant challenge in age estimation tasks. Most existing methods address this issue by modeling correlations between adjacent age groups through label distribution learning. However, they often overlook the varying degrees of ambiguity present across different age stages. In this paper, we propose a Stage-wise Adaptive Label Distribution Learning (SA-LDL) algorithm, which leverages the observation -- revealed through our analysis of embedding similarities between an anchor and all other ages -- that label ambiguity exhibits clear stage-wise patterns. By jointly employing stage-wise adaptive variance modeling and weighted loss function, SA-LDL effectively captures the complex and structured nature of label ambiguity, leading to more accurate and robust age estimation. Extensive experiments demonstrate that SA-LDL achieves competitive performance, with MAE of 1.74 and 2.15 on the MORPH-II and FG-NET datasets.

cs.CV↗

arXiv2025

VoxAging: Continuously Tracking Speaker Aging with a Large-Scale Longitudinal Dataset in English and Mandarin

The performance of speaker verification systems is adversely affected by speaker aging. However, due to challenges in data collection, particularly the lack of sustained and large-scale longitudinal data for individuals, research on speaker aging remains difficult. In this paper, we present VoxAging, a large-scale longitudinal dataset collected from 293 speakers (226 English speakers and 67 Mandarin speakers) over several years, with the longest time span reaching 17 years (approximately 900 weeks). For each speaker, the data were recorded at weekly intervals. We studied the phenomenon of speaker aging and its effects on advanced speaker verification systems, analyzed individual speaker aging processes, and explored the impact of factors such as age group and gender on speaker aging research.

cs.SD↗

arXiv2024

StyleFusion TTS: Multimodal Style-control and Enhanced Feature Fusion for Zero-shot Text-to-speech Synthesis

We introduce StyleFusion-TTS, a prompt and/or audio referenced, style and speaker-controllable, zero-shot text-to-speech (TTS) synthesis system designed to enhance the editability and naturalness of current research literature. We propose a general front-end encoder as a compact and effective module to utilize multimodal inputs including text prompts, audio references, and speaker timbre references in a fully zero-shot manner and produce disentangled style and speaker control embeddings. Our novel approach also leverages a hierarchical conformer structure for the fusion of style and speaker control embeddings, aiming to achieve optimal feature fusion within the current advanced TTS architecture. StyleFusion-TTS is evaluated through multiple metrics, both subjectively and objectively. The system shows promising performance across our evaluations, suggesting its potential to contribute to the advancement of the field of zero-shot text-to-speech synthesis.

eess.AS↗

arXiv2024

Enhancing Open-Set Speaker Identification through Rapid Tuning with Speaker Reciprocal Points and Negative Sample

This paper introduces a novel framework for open-set speaker identification in household environments, playing a crucial role in facilitating seamless human-computer interactions. Addressing the limitations of current speaker models and classification approaches, our work integrates an pretrained WavLM frontend with a few-shot rapid tuning neural network (NN) backend for enrollment, employing task-optimized Speaker Reciprocal Points Learning (SRPL) to enhance discrimination across multiple target speakers. Furthermore, we propose an enhanced version of SRPL (SRPL+), which incorporates negative sample learning with both speech-synthesized and real negative samples to significantly improve open-set SID accuracy. Our approach is thoroughly evaluated across various multi-language text-dependent speaker recognition datasets, demonstrating its effectiveness in achieving high usability for complex household multi-speaker recognition scenarios. The proposed system enhanced open-set performance by up to 27\% over the directly use of efficient WavLM base+ model.

eess.AS↗

arXiv2024

MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spotting

In this paper, we propose MM-KWS, a novel approach to user-defined keyword spotting leveraging multi-modal enrollments of text and speech templates. Unlike previous methods that focus solely on either text or speech features, MM-KWS extracts phoneme, text, and speech embeddings from both modalities. These embeddings are then compared with the query speech embedding to detect the target keywords. To ensure the applicability of MM-KWS across diverse languages, we utilize a feature extractor incorporating several multilingual pre-trained models. Subsequently, we validate its effectiveness on Mandarin and English tasks. In addition, we have integrated advanced data augmentation tools for hard case mining to enhance MM-KWS in distinguishing confusable words. Experimental results on the LibriPhrase and WenetPhrase datasets demonstrate that MM-KWS outperforms prior methods significantly.

eess.AS↗