arXiv subjects

Xuan Shi

Publications and source records attributed to Xuan Shi.

At least 19 recordsLinked to original sources

arXiv2026

ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood

We present ChildVox, a novel benchmark for characterizing the diverse acoustic signals through which children communicate. Specifically, ChildVox follows the full developmental trajectory from birth through school age, covering physiological sounds, non-linguistic vocalizations, canonical syllables, and spoken language. ChildVox integrates more than 20 sub-tasks across 17 child-centered audio and speech datasets, enabling systematic cross-corpus and cross-domain comparison. We evaluate a representative range of audio and speech foundation models, including self-supervised, ASR-oriented, and large audio-language models, on tasks including physiological sound classification, vocalization and canonical syllables modeling, and speech quality assessment and recognition. Benchmark results show that ChildVox provides a suite of high-performance models in recognizing a wide range of acoustic signals from children, supporting downstream applications such as characterizing children's language levels and tracking speech production with age.

cs.SD↗

arXiv2026

Towards Interpretable Framework for Neural Audio Codecs via Sparse Autoencoders: A Case Study on Accent Information

Neural Audio Codecs (NACs) are widely adopted in modern speech systems, yet how they encode linguistic and paralinguistic information remains unclear. Improving the interpretability of NAC representations is critical for understanding and deploying them in sensitive applications. Hence, we employ Sparse Autoencoders (SAEs) to decompose dense NAC representations into sparse, interpretable activations. In this work, we focus on a challenging paralinguistic attribute-accent-and propose a framework to quantify NAC interpretability. We evaluate four NAC models under 16 SAE configurations using a relative performance index. Our results show that DAC and SpeechTokenizer achieve the highest interpretability. We further reveal that acoustic-oriented NACs encode accent information primarily in activation magnitudes of sparse representations, whereas phonetic-oriented NACs rely more on activation positions, and that low-bitrate EnCodec variants show higher interpretability.

cs.SD↗

arXiv2026

Speech Codec Probing from Semantic and Phonetic Perspectives

Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. Speech tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation tasks. However, emerging evidence suggests that the term "semantic" in speech processing does not align with linguistic lexical-semantic, leading to a mismatch between speech and text modality. In this paper, we systematically analyze the information encoded by several widely used speech tokenizers, evaluating their lexical-semantic and phonetic content through three tasks. Our results show that current tokenizers primarily capture phonetic rather than lexical-semantic structure, deriving practical implications for the design of next-generation speech tokenization methods. Code is released to public at https://github.com/Alexuan/codec_probing_release.

eess.AS↗

arXiv2026

An Approach to Simultaneous Acquisition of Real-Time MRI Video, EEG, and Surface EMG for Articulatory, Brain, and Muscle Activity During Speech Production

Speech production is a complex process spanning neural planning, motor control, muscle activation, and articulatory kinematics. While the acoustic speech signal is the most accessible product of the speech production act, it does not directly reveal its causal neurophysiological substrates. We present the first simultaneous acquisition of real-time (dynamic) MRI, EEG, and surface EMG, capturing several key aspects of the speech production chain: brain signals, muscle activations, and articulatory movements. This multimodal acquisition paradigm presents substantial technical challenges, including MRI-induced electromagnetic interference and myogenic artifacts. To mitigate these, we introduce an artifact suppression pipeline tailored to this tri-modal setting. Once fully developed, this framework is poised to offer an unprecedented window into speech neuroscience and insights leading to brain-computer interface advances. The source code and data are available.

eess.AS↗

arXiv2025

A long-form single-speaker real-time MRI speech dataset and benchmark

We release the USC Long Single-Speaker (LSS) dataset containing real-time MRI video of the vocal tract dynamics and simultaneous audio obtained during speech production. This unique dataset contains roughly one hour of video and audio data from a single native speaker of American English, making it one of the longer publicly available single-speaker datasets of real-time MRI speech data. Along with the articulatory and acoustic raw data, we release derived representations of the data that are suitable for a range of downstream tasks. This includes video cropped to the vocal tract region, sentence-level splits of the data, restored and denoised audio, and regions-of-interest timeseries. We also benchmark this dataset on articulatory synthesis and phoneme recognition tasks, providing baseline performance for these tasks on this dataset which future research can aim to improve upon.

cs.SD↗

arXiv2025

Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe

We present Voxlect, a novel benchmark for modeling dialects and regional languages worldwide using speech foundation models. Specifically, we report comprehensive benchmark evaluations on dialects and regional language varieties in English, Arabic, Mandarin and Cantonese, Tibetan, Indic languages, Thai, Spanish, French, German, Brazilian Portuguese, and Italian. Our study used over 2 million training utterances from 30 publicly available speech corpora that are provided with dialectal information. We evaluate the performance of several widely used speech foundation models in classifying speech dialects. We assess the robustness of the dialectal models under noisy conditions and present an error analysis that highlights modeling results aligned with geographic continuity. In addition to benchmarking dialect classification, we demonstrate several downstream applications enabled by Voxlect. Specifically, we show that Voxlect can be applied to augment existing speech recognition datasets with dialect information, enabling a more detailed analysis of ASR performance across dialectal variations. Voxlect is also used as a tool to evaluate the performance of speech generation systems. Voxlect is publicly available with the license of the RAIL family at: https://github.com/tiantiaf0627/voxlect.

cs.SD↗

arXiv2025

Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits

We introduce Vox-Profile, a comprehensive benchmark to characterize rich speaker and speech traits using speech foundation models. Unlike existing works that focus on a single dimension of speaker traits, Vox-Profile provides holistic and multi-dimensional profiles that reflect both static speaker traits (e.g., age, sex, accent) and dynamic speech properties (e.g., emotion, speech flow). This benchmark is grounded in speech science and linguistics, developed with domain experts to accurately index speaker and speech characteristics. We report benchmark experiments using over 15 publicly available speech datasets and several widely used speech foundation models that target various static and dynamic speaker and speech properties. In addition to benchmark experiments, we showcase several downstream applications supported by Vox-Profile. First, we show that Vox-Profile can augment existing speech recognition datasets to analyze ASR performance variability. Vox-Profile is also used as a tool to evaluate the performance of speech generation systems. Finally, we assess the quality of our automated profiles through comparison with human evaluation and show convergent validity. Vox-Profile is publicly available at: https://github.com/tiantiaf0627/vox-profile-release.

cs.SD↗

arXiv2024

Speech2rtMRI: Speech-Guided Diffusion Model for Real-time MRI Video of the Vocal Tract during Speech

Understanding speech production both visually and kinematically can inform second language learning system designs, as well as the creation of speaking characters in video games and animations. In this work, we introduce a data-driven method to visually represent articulator motion in Magnetic Resonance Imaging (MRI) videos of the human vocal tract during speech based on arbitrary audio or speech input. We leverage large pre-trained speech models, which are embedded with prior knowledge, to generalize the visual domain to unseen data using a speech-to-video diffusion model. Our findings demonstrate that the visual generation significantly benefits from the pre-trained speech representations. We also observed that evaluating phonemes in isolation is challenging but becomes more straightforward when assessed within the context of spoken words. Limitations of the current results include the presence of unsmooth tongue motion and video distortion when the tongue contacts the palate.

eess.IV↗

arXiv2024

Examining Test-Time Adaptation for Personalized Child Speech Recognition

Automatic speech recognition (ASR) models often experience performance degradation due to data domain shifts introduced at test time, a challenge that is further amplified for child speakers. Test-time adaptation (TTA) methods have shown great potential in bridging this domain gap. However, the use of TTA to adapt ASR models to the individual differences in each child's speech has not yet been systematically studied. In this work, we investigate the effectiveness of two widely used TTA methods-SUTA, SGEM-in adapting off-the-shelf ASR models and their fine-tuned versions for child speech recognition, with the goal of enabling continuous, unsupervised adaptation at test time. Our findings show that TTA significantly improves the performance of both off-the-shelf and fine-tuned ASR models, both on average and across individual child speakers, compared to unadapted baselines. However, while TTA helps adapt to individual variability, it may still be limited with non-linguistic child speech.

cs.LG↗

arXiv2024

Egocentric Speaker Classification in Child-Adult Dyadic Interactions: From Sensing to Computational Modeling

Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by challenges in social communication, repetitive behavior, and sensory processing. One important research area in ASD is evaluating children's behavioral changes over time during treatment. The standard protocol with this objective is BOSCC, which involves dyadic interactions between a child and clinicians performing a pre-defined set of activities. A fundamental aspect of understanding children's behavior in these interactions is automatic speech understanding, particularly identifying who speaks and when. Conventional approaches in this area heavily rely on speech samples recorded from a spectator perspective, and there is limited research on egocentric speech modeling. In this study, we design an experiment to perform speech sampling in BOSCC interviews from an egocentric perspective using wearable sensors and explore pre-training Ego4D speech samples to enhance child-adult speaker classification in dyadic interactions. Our findings highlight the potential of egocentric speech collection and pre-training to improve speaker classification accuracy.

cs.SD↗

arXiv2024

Toward Fully-End-to-End Listened Speech Decoding from EEG Signals

Speech decoding from EEG signals is a challenging task, where brain activity is modeled to estimate salient characteristics of acoustic stimuli. We propose FESDE, a novel framework for Fully-End-to-end Speech Decoding from EEG signals. Our approach aims to directly reconstruct listened speech waveforms given EEG signals, where no intermediate acoustic feature processing step is required. The proposed method consists of an EEG module and a speech module along with a connector. The EEG module learns to better represent EEG signals, while the speech module generates speech waveforms from model representations. The connector learns to bridge the distributions of the latent spaces of EEG and speech. The proposed framework is both simple and efficient, by allowing single-step inference, and outperforms prior works on objective metrics. A fine-grained phoneme analysis is conducted to unveil model characteristics of speech decoding. The source code is available here: github.com/lee-jhwn/fesde.

eess.SP↗

arXiv2024

TI-ASU: Toward Robust Automatic Speech Understanding through Text-to-speech Imputation Against Missing Speech Modality

Automatic Speech Understanding (ASU) aims at human-like speech interpretation, providing nuanced intent, emotion, sentiment, and content understanding from speech and language (text) content conveyed in speech. Typically, training a robust ASU model relies heavily on acquiring large-scale, high-quality speech and associated transcriptions. However, it is often challenging to collect or use speech data for training ASU due to concerns such as privacy. To approach this setting of enabling ASU when speech (audio) modality is missing, we propose TI-ASU, using a pre-trained text-to-speech model to impute the missing speech. We report extensive experiments evaluating TI-ASU on various missing scales, both multi- and single-modality settings, and the use of LLMs. Our findings show that TI-ASU yields substantial benefits to improve ASU in scenarios where even up to 95% of training speech is missing. Moreover, we show that TI-ASU is adaptive to dropout training, improving model robustness in addressing missing speech during inference.

cs.SD↗

arXiv2023

Unlocking Foundation Models for Privacy-Enhancing Speech Understanding: An Early Study on Low Resource Speech Training Leveraging Label-guided Synthetic Speech Content

Automatic Speech Understanding (ASU) leverages the power of deep learning models for accurate interpretation of human speech, leading to a wide range of speech applications that enrich the human experience. However, training a robust ASU model requires the curation of a large number of speech samples, creating risks for privacy breaches. In this work, we investigate using foundation models to assist privacy-enhancing speech computing. Unlike conventional works focusing primarily on data perturbation or distributed algorithms, our work studies the possibilities of using pre-trained generative models to synthesize speech content as training data with just label guidance. We show that zero-shot learning with training label-guided synthetic speech content remains a challenging task. On the other hand, our results demonstrate that the model trained with synthetic speech samples provides an effective initialization point for low-resource ASU training. This result reveals the potential to enhance privacy by reducing user data collection but using label-guided synthetic speech content.

cs.SD↗

arXiv2022

A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness

Speech-centric machine learning systems have revolutionized many leading domains ranging from transportation and healthcare to education and defense, profoundly changing how people live, work, and interact with each other. However, recent studies have demonstrated that many speech-centric ML systems may need to be considered more trustworthy for broader deployment. Specifically, concerns over privacy breaches, discriminating performance, and vulnerability to adversarial attacks have all been discovered in ML research fields. In order to address the above challenges and risks, a significant number of efforts have been made to ensure these ML systems are trustworthy, especially private, safe, and fair. In this paper, we conduct the first comprehensive survey on speech-centric trustworthy ML topics related to privacy, safety, and fairness. In addition to serving as a summary report for the research community, we point out several promising future research directions to inspire the researchers who wish to explore further in this area.

cs.SD↗

arXiv2022

Can Knowledge of End-to-End Text-to-Speech Models Improve Neural MIDI-to-Audio Synthesis Systems?

With the similarity between music and speech synthesis from symbolic input and the rapid development of text-to-speech (TTS) techniques, it is worthwhile to explore ways to improve the MIDI-to-audio performance by borrowing from TTS techniques. In this study, we analyze the shortcomings of a TTS-based MIDI-to-audio system and improve it in terms of feature computation, model selection, and training strategy, aiming to synthesize highly natural-sounding audio. Moreover, we conducted an extensive model evaluation through listening tests, pitch measurement, and spectrogram analysis. This work demonstrates not only synthesis of highly natural music but offers a thorough analytical approach and useful outcomes for the community. Our code, pre-trained models, supplementary materials, and audio samples are open sourced at https://github.com/nii-yamagishilab/midi-to-audio.

cs.SD↗

arXiv2021

Use of speaker recognition approaches for learning and evaluating embedding representations of musical instrument sounds

Constructing an embedding space for musical instrument sounds that can meaningfully represent new and unseen instruments is important for downstream music generation tasks such as multi-instrument synthesis and timbre transfer. The framework of Automatic Speaker Verification (ASV) provides us with architectures and evaluation methodologies for verifying the identities of unseen speakers, and these can be repurposed for the task of learning and evaluating a musical instrument sound embedding space that can support unseen instruments. Borrowing from state-of-the-art ASV techniques, we construct a musical instrument recognition model that uses a SincNet front-end, a ResNet architecture, and an angular softmax objective function. Experiments on the NSynth and RWC datasets show our model's effectiveness in terms of equal error rate (EER) for unseen instruments, and ablation studies show the importance of data augmentation and the angular softmax objective. Experiments also show the benefit of using a CQT-based filterbank for initializing SincNet over a Mel filterbank initialization. Further complementary analysis of the learned embedding space is conducted with t-SNE visualizations and probing classification tasks, which show that including instrument family labels as a multi-task learning target can help to regularize the embedding space and incorporate useful structure, and that meaningful information such as playing style, which was not included during training, is contained in the embeddings of unseen instruments.

eess.AS↗

arXiv2020

Taming Near Repeat Calculation for Crime Analysis via Cohesive Subgraph Computing

Near repeat (NR) is a well known phenomenon in crime analysis assuming that crime events exhibit correlations within a given time and space frame. Traditional NR calculation generates 2 event pairs if 2 events happened within a given space and time limit. When the number of events is large, however, NR calculation is time consuming and how these pairs are organized are not yet explored. In this paper, we designed a new approach to calculate clusters of NR events efficiently. To begin with, R-tree is utilized to index crime events, a single event is represented by a vertex whereas edges are constructed by range querying the vertex in R-tree, and a graph is formed. Cohesive subgraph approaches are applied to identify the event chains. k-clique, k-truss, k-core plus DBSCAN algorithms are implemented in sequence with respect to their varied range of ability to find cohesive subgraphs. Real world crime data in Chicago, New York and Washington DC are utilized to conduct experiments. The experiment confirmed that near repeat is a solid effect in real big crime data by conducting Mapreduce empowered knox tests. The performance of 4 different algorithms are validated, while the quality of the algorithms are gauged by the distribution of number of cohesive subgraphs and their clustering coefficients. The proposed framework is the first to process the real crime data of million record scale, and is the first to detect NR events with size of more than 2.

cs.DS↗

arXiv2019

RepGN:Object Detection with Relational Proposal Graph Network

Region based object detectors achieve the state-of-the-art performance, but few consider to model the relation of proposals. In this paper, we explore the idea of modeling the relationships among the proposals for object detection from the graph learning perspective. Specifically, we present relational proposal graph network (RepGN) which is defined on object proposals and the semantic and spatial relation modeled as the edge. By integrating our RepGN module into object detectors, the relation and context constraints will be introduced to the feature extraction of regions and bounding boxes regression and classification. Besides, we propose a novel graph-cut based pooling layer for hierarchical coarsening of the graph, which empowers the RepGN module to exploit the inter-regional correlation and scene description in a hierarchical manner. We perform extensive experiments on COCO object detection dataset and show promising results.

cs.CV↗