arXiv subjects

Yanpei Shi

Publications and source records attributed to Yanpei Shi.

13 recordsLinked to original sources

arXiv2025

NaviSense: A Multimodal Assistive Mobile application for Object Retrieval by Persons with Visual Impairment

People with visual impairments often face significant challenges in locating and retrieving objects in their surroundings. Existing assistive technologies present a trade-off: systems that offer precise guidance typically require pre-scanning or support only fixed object categories, while those with open-world object recognition lack spatial feedback for reaching the object. To address this gap, we introduce 'NaviSense', a mobile assistive system that combines conversational AI, vision-language models, augmented reality (AR), and LiDAR to support open-world object detection with real-time audio-haptic guidance. Users specify objects via natural language and receive continuous spatial feedback to navigate toward the target without needing prior setup. Designed with insights from a formative study and evaluated with 12 blind and low-vision participants, NaviSense significantly reduced object retrieval time and was preferred over existing tools, demonstrating the value of integrating open-world perception with precise, accessible guidance.

cs.HC↗

arXiv2025

Compact Amplified Laser Power Stabilization Using Robust Active Disturbance Rejection Control with Sensor Noise Decoupling

Laser power instability, encompassing random jitter and slow drift, severely limits the performance of optically pumped magnetometers (OPMs) in detecting ultra-weak magnetic fields, especially in large-scale OPM arrays for magnetoencephalography. Although a unified amplified laser (AL) architecture improves integration, fluctuations in the pump beam progressively degrade performance across all channels, exacerbated by environmental disturbances and system uncertainties. To address this challenge, this paper presents a compact AL power stabilization approach based on an innovative dual-loop active disturbance rejection control (DLADRC) strategy, while integrating a comprehensive quantitative stability analysis through novel exponential decay estimates for extended state observers (ESOs) and control error dynamics. As validated through physical experimental results, the proposed method significantly improves AL's long-term stability with sensor noise decoupling, achieving an over 85.7% reduction in 1-hour power instability and a tenfold decrease in Allan variance for correlation times 10^2 s--10^3 s, compared to standard ADRC. Crucially, the strategy demonstrates robust effectiveness across diverse operating scenarios, enabling AL-based OPM systems to achieve their full potential in high-sensitivity biomagnetic field detection.

eess.SY↗

arXiv2025

Physics-Informed Neural Network for Cross-Domain Predictive Control of Tapered Amplifier Thermal Stabilization

Thermally induced laser noise poses a critical limitation to the sensitivity of quantum sensor arrays employing ultra-stable amplified lasers, primarily stemming from nonlinear gain-temperature coupling effects in tapered amplifiers (TAs). To address this challenge, we present a robust intelligent control strategy that synergistically integrates an encoder-decoder physics-informed gated recurrent unit (PI-GRU) network with a model predictive control (MPC) framework. Our methodology incorporates physical soft constraints into the neural network architecture, yielding a predictive model with enhanced physical consistency that demonstrates robust extrapolation capabilities beyond the training data distribution. Leveraging the PI-GRU model's accurate multi-step predictive performance, we implement a hierarchical parallel MPC architecture capable of real-time thermal instability compensation. This hybrid approach achieves cross-domain consistent thermal stabilization in TAs under diverse laser power operations. Remarkably, while trained exclusively on low-power operational data, our system demonstrates exceptional generalization, improving prediction accuracy by 58.2% and temperature stability by 69.1% in previously unseen high-power operating regimes, as experimentally validated. The novel synchronization of physics-informed neural networks with advanced MPC frameworks presented in this work establishes a groundbreaking paradigm for addressing robustness challenges in cross-domain predictive control applications, overcoming conventional modeling limitations.

eess.SY↗

arXiv2024

Swin-BERT: A Feature Fusion System designed for Speech-based Alzheimer's Dementia Detection

Speech is usually used for constructing an automatic Alzheimer's dementia (AD) detection system, as the acoustic and linguistic abilities show a decline in people living with AD at the early stages. However, speech includes not only AD-related local and global information but also other information unrelated to cognitive status, such as age and gender. In this paper, we propose a speech-based system named Swin-BERT for automatic dementia detection. For the acoustic part, the shifted windows multi-head attention that proposed to extract local and global information from images, is used for designing our acoustic-based system. To decouple the effect of age and gender on acoustic feature extraction, they are used as an extra input of the designed acoustic system. For the linguistic part, the rhythm-related information, which varies significantly between people living with and without AD, is removed while transcribing the audio recordings into transcripts. To compensate for the removed rhythm-related information, the character-level transcripts are proposed to be used as the extra input of a word-level BERT-style system. Finally, the Swin-BERT combines the acoustic features learned from our proposed acoustic-based system with our linguistic-based system. The experiments are based on the two datasets provided by the international dementia detection challenges: the ADReSS and ADReSSo. The results show that both the proposed acoustic and linguistic systems can be better or comparable with previous research on the two datasets. Superior results are achieved by the proposed Swin-BERT system on the ADReSS and ADReSSo datasets, which are 85.58\% F-score and 87.32\% F-score respectively.

eess.AS↗

arXiv2021

Contextual Joint Factor Acoustic Embeddings

Embedding acoustic information into fixed length representations is of interest for a whole range of applications in speech and audio technology. Two novel unsupervised approaches to generate acoustic embeddings by modelling of acoustic context are proposed. The first approach is a contextual joint factor synthesis encoder, where the encoder in an encoder/decoder framework is trained to extract joint factors from surrounding audio frames to best generate the target output. The second approach is a contextual joint factor analysis encoder, where the encoder is trained to analyse joint factors from the source signal that correlates best with the neighbouring audio. To evaluate the effectiveness of our approaches compared to prior work, two tasks are conducted -- phone classification and speaker recognition -- and test on different TIMIT data sets. Experimental results show that one of the proposed approaches outperforms phone classification baselines, yielding a classification accuracy of 74.1%. When using additional out-of-domain data for training, an additional 3% improvements can be obtained, for both for phone classification and speaker recognition tasks.

cs.CL↗

arXiv2021

Supervised Speaker Embedding De-Mixing in Two-Speaker Environment

Separating different speaker properties from a multi-speaker environment is challenging. Instead of separating a two-speaker signal in signal space like speech source separation, a speaker embedding de-mixing approach is proposed. The proposed approach separates different speaker properties from a two-speaker signal in embedding space. The proposed approach contains two steps. In step one, the clean speaker embeddings are learned and collected by a residual TDNN based network. In step two, the two-speaker signal and the embedding of one of the speakers are both input to a speaker embedding de-mixing network. The de-mixing network is trained to generate the embedding of the other speaker by reconstruction loss. Speaker identification accuracy and the cosine similarity score between the clean embeddings and the de-mixed embeddings are used to evaluate the quality of the obtained embeddings. Experiments are done in two kind of data: artificial augmented two-speaker data (TIMIT) and real world recording of two-speaker data (MC-WSJ). Six different speaker embedding de-mixing architectures are investigated. Comparing with the performance on the clean speaker embeddings, the obtained results show that one of the proposed architectures obtained close performance, reaching 96.9% identification accuracy and 0.89 cosine similarity.

cs.SD↗

arXiv2020

T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. This paper proposes a hierarchical network with transformer encoders and memory mechanism to address this problem. The proposed model contains a frame-level encoder and segment-level encoder, both of them make use of the transformer encoder block. The multi-head attention mechanism in the transformer structure could better capture different speaker properties when the input utterance contains multiple speakers. The memory mechanism used in the frame-level encoders can build a recurrent connection that better capture long-term speaker features. The experiments are conducted on artificial datasets based on the Switchboard Cellular part1 (SWBC) and Voxceleb1 datasets. In different data construction scenarios (Concat and Overlap), the proposed model shows better performance comparaing with four strong baselines, reaching 13.3% and 10.5% relative improvement compared with H-vectors and S-vectors. The use of memory mechanism could reach 10.6% and 7.7% relative improvement compared with not using memory mechanism.

cs.SD↗

arXiv2020

Towards Low-Resource StarGAN Voice Conversion using Weight Adaptive Instance Normalization

Many-to-many voice conversion with non-parallel training data has seen significant progress in recent years. StarGAN-based models have been interests of voice conversion. However, most of the StarGAN-based methods only focused on voice conversion experiments for the situations where the number of speakers was small, and the amount of training data was large. In this work, we aim at improving the data efficiency of the model and achieving a many-to-many non-parallel StarGAN-based voice conversion for a relatively large number of speakers with limited training samples. In order to improve data efficiency, the proposed model uses a speaker encoder for extracting speaker embeddings and conducts adaptive instance normalization (AdaIN) on convolutional weights. Experiments are conducted with 109 speakers under two low-resource situations, where the number of training samples is 20 and 5 per speaker. An objective evaluation shows the proposed model is better than the baseline methods. Furthermore, a subjective evaluation shows that, for both naturalness and similarity, the proposed model outperforms the baseline method.

cs.SD↗

arXiv2020

Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. In this paper, a hierarchical attention network is proposed to solve a weakly labelled speaker identification problem. The use of a hierarchical structure, consisting of a frame-level encoder and a segment-level encoder, aims to learn speaker related information locally and globally. Speech streams are segmented into fragments. The frame-level encoder with attention learns features and highlights the target related frames locally, and output a fragment based embedding. The segment-level encoder works with a second attention layer to emphasize the fragments probably related to target speakers. The global information is finally collected from segment-level module to predict speakers via a classifier. To evaluate the effectiveness of the proposed approach, artificial datasets based on Switchboard Cellular part1 (SWBC) and Voxceleb1 are constructed in two conditions, where speakers' voices are overlapped and not overlapped. Comparing to two baselines the obtained results show that the proposed approach can achieve better performances. Moreover, further experiments are conducted to evaluate the impact of utterance segmentation. The results show that a reasonable segmentation can slightly improve identification performances.

eess.AS↗

arXiv2020

Speaker Re-identification with Speaker Dependent Speech Enhancement

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved performance. The recent works have shown that adapting speech enhancement can lead to further gains. This paper introduces a novel approach that cascades speech enhancement and speaker recognition. In the first step, a speaker embedding vector is generated , which is used in the second step to enhance the speech quality and re-identify the speakers. Models are trained in an integrated framework with joint optimisation. The proposed approach is evaluated using the Voxceleb1 dataset, which aims to assess speaker recognition in real world situations. In addition three types of noise at different signal-noise-ratios were added for this work. The obtained results show that the proposed approach using speaker dependent speech enhancement can yield better speaker recognition and speech enhancement performances than two baselines in various noise conditions.

eess.AS↗

arXiv2020

Robust Speaker Recognition Using Speech Enhancement And Attention Model

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of individually processing speech enhancement and speaker recognition, the two modules are integrated into one framework by a joint optimisation using deep neural networks. Furthermore, to increase robustness against noise, a multi-stage attention mechanism is employed to highlight the speaker related features learned from context information in time and frequency domain. To evaluate speaker identification and verification performance of the proposed approach, we test it on the dataset of VoxCeleb1, one of mostly used benchmark datasets. Moreover, the robustness of our proposed approach is also tested on VoxCeleb1 data when being corrupted by three types of interferences, general noise, music, and babble, at different signal-to-noise ratio (SNR) levels. The obtained results show that the proposed approach using speech enhancement and multi-stage attention models outperforms two strong baselines not using them in most acoustic conditions in our experiments.

cs.CL↗

arXiv2020

Improving Noise Robustness In Speaker Identification Using A Two-Stage Attention Model

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in noise, a novel two-stage attention mechanism which can be used in existing architectures such as Time Delay Neural Networks (TDNNs) and Convolutional Neural Networks (CNNs) is proposed. Noise is known to often mask important information in both time and frequency domain. The proposed mechanism allows the models to concentrate on reliable time/frequency components of the signal. The proposed approach is evaluated using the Voxceleb1 dataset, which aims at assessment of speaker recognition in real world situations. In addition three types of noise at different signal-noise-ratios (SNRs) were added for this work. The proposed mechanism is compared with three strong baselines: X-vectors, Attentive X-vector, and Resnet-34. Results on both identification and verification tasks show that the two-stage attention mechanism consistently improves upon these for all noise conditions.

eess.AS↗

arXiv2019

H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model

In this paper, a hierarchical attention network to generate utterance-level embeddings (H-vectors) for speaker identification is proposed. Since different parts of an utterance may have different contributions to speaker identities, the use of hierarchical structure aims to learn speaker related information locally and globally. In the proposed approach, frame-level encoder and attention are applied on segments of an input utterance and generate individual segment vectors. Then, segment level attention is applied on the segment vectors to construct an utterance representation. To evaluate the effectiveness of the proposed approach, NIST SRE 2008 Part1 dataset is used for training, and two datasets, Switchboard Cellular part1 and CallHome American English Speech, are used to evaluate the quality of extracted utterance embeddings on speaker identification and verification tasks. In comparison with two baselines, X-vector, X-vector+Attention, the obtained results show that H-vectors can achieve a significantly better performance. Furthermore, the extracted utterance-level embeddings are more discriminative than the two baselines when mapped into a 2D space using t-SNE.

cs.CL↗