arXiv subjects

Jianbo Ma

Publications and source records attributed to Jianbo Ma.

16 recordsLinked to original sources

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

Joint Learning of Covariance Estimation and White Noise Gain for Robust MVDR Beamforming

The minimum variance distortionless response (MVDR) beamformer is widely used for multichannel speech enhancement due to strong noise suppression while preserving target signals. In practice, its performance is sensitive to microphone self-noise and array mismatches. Existing approaches typically rely on fixed, manually tuned WNG thresholds or diagonal loading, leading to suboptimal performance under unknown or time-varying acoustic conditions. This paper proposes a data-driven MVDR framework that adaptively estimates the WNG constraint using a deep neural network. The network jointly predicts a time-frequency noise mask for covariance estimation and a frequency-dependent WNG threshold, enabling dynamic robustness-directivity control. A differentiable robust MVDR layer is integrated into the framework, allowing end-to-end optimization. Experiments demonstrate consistent improvements in speech quality and intelligibility over conventional fixed-WNG MVDR methods.

eess.AS↗

arXiv2026

Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance

Vision-Language Models (VLMs) have enhanced traditional LLMs with visual capabilities through the integration of vision encoders. While recent works have explored various combinations of vision encoders and LLMs, there still lacks a principled understanding of what makes a vision encoder suitable for VLM alignment. In this paper, we systematically investigate this question via comprehensive experiments on a curated collection of 19 pre-trained vision encoders from diverse sources. We first demonstrate that common practices, such as choosing encoders with the largest size or highest zero-shot accuracy, consistently fail to identify optimal models. In fact, these metrics show only weak to moderate correlation with VLM performance. This intriguing finding begs a fundamental question: What factors of vision-encoders matter in VLM? Through comprehensive analysis, we identify that the structural similarity across modalities plays a crucial but previously overlooked role in vision-encoder selection, which we measure using the Gromov-Wasserstein distance as a proxy. From a theoretical perspective, we show that the learnability of cross-modality mapping can be provably associated with the Gromov-Wasserstein distance. Empirical verification on 60+ full VLM training runs shows that our proposed inference-only metric performs significantly better than alternative model selection strategies and exhibits a much stronger correlation with final VLM performance, thereby enabling efficient and effective prediction of VLM performance before full training.

cs.CV↗

arXiv2026

Text-To-Speech with Chain-of-Details: modeling temporal dynamics in speech generation

Recent advances in Text-To-Speech (TTS) synthesis have seen the popularity of multi-stage approaches that first predict semantic tokens and then generate acoustic tokens. In this paper, we extend the coarse-to-fine generation paradigm to the temporal domain and introduce Chain-of-Details (CoD), a novel framework that explicitly models temporal coarse-to-fine dynamics in speech generation using a cascaded architecture. Our method progressively refines temporal details across multiple stages, with each stage targeting a specific temporal granularity. All temporal detail predictions are performed using a shared decoder, enabling efficient parameter utilization across different temporal resolutions. Notably, we observe that the lowest detail level naturally performs phonetic planning without the need for an explicit phoneme duration predictor. We evaluate our method on several datasets and compare it against several baselines. Experimental results show that CoD achieves competitive performance with significantly fewer parameters than existing approaches. Our findings demonstrate that explicit modeling of temporal dynamics with the CoD framework leads to more natural speech synthesis.

eess.AS↗

arXiv2026

Occlusion-Aware SORT: Observing Occlusion for Robust Multi-Object Tracking

Multi-object tracking (MOT) involves analyzing object trajectories and counting the number of objects in video sequences. However, 2D MOT faces challenges due to positional cost confusion arising from partial occlusion. To address this issue, we present the novel Occlusion-Aware SORT (OA-SORT) framework, a plug-and-play and training-free framework that includes the Occlusion-Aware Module (OAM), the Occlusion-Aware Offset (OAO), and the Bias-Aware Momentum (BAM). Specifically, OAM analyzes the occlusion status of objects, where a Gaussian Map (GM) is introduced to reduce background influence. In contrast, OAO and BAM leverage the OAM-described occlusion status to mitigate cost confusion and suppress estimation instability. Comprehensive evaluations on the DanceTrack, SportsMOT, and MOT17 datasets demonstrate the importance of occlusion handling in MOT. On the DanceTrack test set, OA-SORT achieves 63.1% and 64.2% in HOTA and IDF1, respectively. Furthermore, integrating the Occlusion-Aware framework into the four additional trackers improves HOTA and IDF1 by an average of 2.08% and 3.05%, demonstrating the reusability of the occlusion awareness.

cs.CV↗

arXiv2025

Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos

Multi-object tracking (MOT) aims to track multiple objects while maintaining consistent identities across frames of a given video. In unmanned aerial vehicle (UAV) recorded videos, frequent viewpoint changes and complex UAV-ground relative motion dynamics pose significant challenges, which often lead to unstable affinity measurement and ambiguous association. Existing methods typically model motion and appearance cues separately, overlooking their spatio-temporal interplay and resulting in suboptimal tracking performance. In this work, we propose AMOT, which jointly exploits appearance and motion cues through two key components: an Appearance-Motion Consistency (AMC) matrix and a Motion-aware Track Continuation (MTC) module. Specifically, the AMC matrix computes bi-directional spatial consistency under the guidance of appearance features, enabling more reliable and context-aware identity association. The MTC module complements AMC by reactivating unmatched tracks through appearance-guided predictions that align with Kalman-based predictions, thereby reducing broken trajectories caused by missed detections. Extensive experiments on three UAV benchmarks, including VisDrone2019, UAVDT, and VT-MOT-UAV, demonstrate that our AMOT outperforms current state-of-the-art methods and generalizes well in a plug-and-play and training-free manner.

cs.CV↗

arXiv2025

Beyond Video-to-SFX: Video to Audio Synthesis with Environmentally Aware Speech

The generation of realistic, context-aware audio is important in real-world applications such as video game development. While existing video-to-audio (V2A) methods mainly focus on Foley sound generation, they struggle to produce intelligible speech. Meanwhile, current environmental speech synthesis approaches remain text-driven and fail to temporally align with dynamic video content. In this paper, we propose Beyond Video-to-SFX (BVS), a method to generate synchronized audio with environmentally aware intelligible speech for given videos. We introduce a two-stage modeling method: (1) stage one is a video-guided audio semantic (V2AS) model to predict unified audio semantic tokens conditioned on phonetic cues; (2) stage two is a video-conditioned semantic-to-acoustic (VS2A) model that refines semantic tokens into detailed acoustic tokens. Experiments demonstrate the effectiveness of BVS in scenarios such as video-to-context-aware speech synthesis and immersive audio background conversion, with ablation studies further validating our design. Our demonstration is available at~\href{https://xinleiniu.github.io/BVS-demo/}{BVS-Demo}.

cs.SD↗

arXiv2025

Gotta Hear Them All: Towards Sound Source Aware Audio Generation

Audio synthesis has broad applications in multimedia. Recent advancements have made it possible to generate relevant audios from inputs describing an audio scene, such as images or texts. However, the immersiveness and expressiveness of the generation are limited. One possible problem is that existing methods solely rely on the global scene and overlook details of local sounding objects (i.e., sound sources). To address this issue, we propose a Sound Source-Aware Audio (SS2A) generator. SS2A is able to locally perceive multimodal sound sources from a scene with visual detection and cross-modality translation. It then contrastively learns a Cross-Modal Sound Source (CMSS) Manifold to semantically disambiguate each source. Finally, we attentively mix their CMSS semantics into a rich audio representation, from which a pretrained audio generator outputs the sound. To model the CMSS manifold, we curate a novel single-sound-source visual-audio dataset VGGS3 from VGGSound. We also design a Sound Source Matching Score to clearly measure localized audio relevance. With the effectiveness of explicit sound source modeling, SS2A achieves state-of-the-art performance in extensive image-to-audio tasks. We also qualitatively demonstrate SS2A's ability to achieve intuitive synthesis control by compositing vision, text, and audio conditions. Furthermore, we show that our sound source modeling can achieve competitive video-to-audio performance with a straightforward temporal aggregation mechanism.

cs.MM↗

arXiv2025

Hydrogen diffusion in ceria: solid state NMR, combined scattering and spectroscopic studies, and ab initio calculations

Ceria has been extensively studied since it has many applications in diverse research fields. However, the mechanism of the hydrogen dynamics, especially the diffusion kinetics on a microscopic level is still unclear as the experimental data has been very limited. In this work, the CeO$_2$-H interaction has been comprehensively studied by a combination of $^1$H NMR transverse relaxation time ($T_2$) measurement, neutron powder diffraction, quasi-elastic neutron scattering (QENS), X-ray total scattering, and ab initio calculations. Based on QENS measurements, the first direct evidence for hydrogen jump diffusions of the Chudley-Elliot type in the bulk ceria has been given, with a jump distance of ~3.98 angstrom. The theoretically calculated activation energy barriers $E_a$ for hydrogen diffusion are relatively low (less than 0.1 eV), further supporting that such hopping can readily occur. A larger barrier value of $E_a$ ~0.2 eV is directly estimated by $T_2$ NMR data, suggesting possible slower hydrogen dynamics with the pre-exponential factor $D_0$ of diffusion coefficient ~10$^{-11}$ m$^2/$s.

cond-mat.mtrl-sci↗

arXiv2024

Diff-SAGe: End-to-End Spatial Audio Generation Using Diffusion Models

Spatial audio is a crucial component in creating immersive experiences. Traditional simulation-based approaches to generate spatial audio rely on expertise, have limited scalability, and assume independence between semantic and spatial information. To address these issues, we explore end-to-end spatial audio generation. We introduce and formulate a new task of generating first-order Ambisonics (FOA) given a sound category and sound source spatial location. We propose Diff-SAGe, an end-to-end, flow-based diffusion-transformer model for this task. Diff-SAGe utilizes a complex spectrogram representation for FOA, preserving the phase information crucial for accurate spatial cues. Additionally, a multi-conditional encoder integrates the input conditions into a unified representation, guiding the generation of FOA waveforms from noise. Through extensive evaluations on two datasets, we demonstrate that our method consistently outperforms traditional simulation-based baselines across both objective and subjective metrics.

cs.SD↗

arXiv2024

STCMOT: Spatio-Temporal Cohesion Learning for UAV-Based Multiple Object Tracking

Multiple object tracking (MOT) in Unmanned Aerial Vehicle (UAV) videos is important for diverse applications in computer vision. Current MOT trackers rely on accurate object detection results and precise matching of target reidentification (ReID). These methods focus on optimizing target spatial attributes while overlooking temporal cues in modelling object relationships, especially for challenging tracking conditions such as object deformation and blurring, etc. To address the above-mentioned issues, we propose a novel Spatio-Temporal Cohesion Multiple Object Tracking framework (STCMOT), which utilizes historical embedding features to model the representation of ReID and detection features in a sequential order. Concretely, a temporal embedding boosting module is introduced to enhance the discriminability of individual embedding based on adjacent frame cooperation. While the trajectory embedding is then propagated by a temporal detection refinement module to mine salient target locations in the temporal field. Extensive experiments on the VisDrone2019 and UAVDT datasets demonstrate our STCMOT sets a new state-of-the-art performance in MOTA and IDF1 metrics. The source codes are released at https://github.com/ydhcg-BoBo/STCMOT.

cs.CV↗

arXiv2024

Rethinking Mamba in Speech Processing by Self-Supervised Models

The Mamba-based model has demonstrated outstanding performance across tasks in computer vision, natural language processing, and speech processing. However, in the realm of speech processing, the Mamba-based model's performance varies across different tasks. For instance, in tasks such as speech enhancement and spectrum reconstruction, the Mamba model performs well when used independently. However, for tasks like speech recognition, additional modules are required to surpass the performance of attention-based models. We propose the hypothesis that the Mamba-based model excels in "reconstruction" tasks within speech processing. However, for "classification tasks" such as Speech Recognition, additional modules are necessary to accomplish the "reconstruction" step. To validate our hypothesis, we analyze the previous Mamba-based Speech Models from an information theory perspective. Furthermore, we leveraged the properties of HuBERT in our study. We trained a Mamba-based HuBERT model, and the mutual information patterns, along with the model's performance metrics, confirmed our assumptions.

eess.AS↗

arXiv2024

A low latency attention module for streaming self-supervised speech representation learning

The transformer is a fundamental building block in deep learning, and the attention mechanism is the transformer's core component. Self-supervised speech representation learning (SSRL) represents a popular use-case for the transformer architecture. Due to transformers' acausal behavior, the use of transformers for SSRL has been predominantly focused on acausal applications. However, several media processing problems, such as speech processing, require real-time solutions. In this paper, we present an implementation of the attention module that enables training of SSRL architectures with low compute and memory requirements, while allowing real-time inference with low and fixed latency. The attention module proposed in this paper includes two components, streaming attention (SA) and low-latency streaming attention (LLSA). The SA represents our proposal for an efficient streaming SSRL implementation, while the LLSA solves the latency build-up problem of other streaming attention architectures, such as the masked acausal attention (MAA), guaranteeing a latency equal to one layer even when multiple layers are stacked. We present a comparative analysis between the vanilla attention, which we will refer here as acausal attention (AA), the SA, and the LLSA, by training a streaming SSRL with automatic speech recognition as downstream task. When training on librispeech-clean-100 and testing on librispeech-test-clean, our low-latency attention module has a word error rate (WER) of 5.84%, which represents a significant improvement over the MAA (WER = 13.82%). Our implementation also reduces the inference latency from 1.92 to 0.16 seconds. The proposed low-latency module preserves many of the benefits of conventional acausal transformers, but also enables latency characteristics that make it applicable to real-time streaming applications.

cs.SD↗

arXiv2024

A unified multichannel far-field speech recognition system: combining neural beamforming with attention based end-to-end model

Far-field speech recognition is a challenging task that conventionally uses signal processing beamforming to attack noise and interference problem. But the performance has been found usually limited due to heavy reliance on environmental assumption. In this paper, we propose a unified multichannel far-field speech recognition system that combines the neural beamforming and transformer-based Listen, Spell, Attend (LAS) speech recognition system, which extends the end-to-end speech recognition system further to include speech enhancement. Such framework is then jointly trained to optimize the final objective of interest. Specifically, factored complex linear projection (fCLP) has been adopted to form the neural beamforming. Several pooling strategies to combine look directions are then compared in order to find the optimal approach. Moreover, information of the source direction is also integrated in the beamforming to explore the usefulness of source direction as a prior, which is usually available especially in multi-modality scenario. Experiments on different microphone array geometry are conducted to evaluate the robustness against spacing variance of microphone array. Large in-house databases are used to evaluate the effectiveness of the proposed framework and the proposed method achieve 19.26\% improvement when compared with a strong baseline.

eess.AS↗

arXiv2023

V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models

Building artificial intelligence (AI) systems on top of a set of foundation models (FMs) is becoming a new paradigm in AI research. Their representative and generative abilities learnt from vast amounts of data can be easily adapted and transferred to a wide range of downstream tasks without extra training from scratch. However, leveraging FMs in cross-modal generation remains under-researched when audio modality is involved. On the other hand, automatically generating semantically-relevant sound from visual input is an important problem in cross-modal generation studies. To solve this vision-to-audio (V2A) generation problem, existing methods tend to design and build complex systems from scratch using modestly sized datasets. In this paper, we propose a lightweight solution to this problem by leveraging foundation models, specifically CLIP, CLAP, and AudioLDM. We first investigate the domain gap between the latent space of the visual CLIP and the auditory CLAP models. Then we propose a simple yet effective mapper mechanism (V2A-Mapper) to bridge the domain gap by translating the visual input between CLIP and CLAP spaces. Conditioned on the translated CLAP embedding, pretrained audio generative FM AudioLDM is adopted to produce high-fidelity and visually-aligned sound. Compared to previous approaches, our method only requires a quick training of the V2A-Mapper. We further analyze and conduct extensive experiments on the choice of the V2A-Mapper and show that a generative mapper is better at fidelity and variability (FD) while a regression mapper is slightly better at relevance (CS). Both objective and subjective evaluation on two V2A datasets demonstrate the superiority of our proposed method compared to current state-of-the-art approaches - trained with 86% fewer parameters but achieving 53% and 19% improvement in FD and CS, respectively.

cs.CV↗

arXiv2020

An ab initio molecular dynamics exploration of associates in Ba-Bi liquid with strong ordering trends

Fictive associates are widely used to describe and model liquid phases with strong ordering trends. However, little evidence is known about the assumed associates in most cases. In the present work, an ab initio molecular dynamics (AIMD) study is employed to investigate the characters of the Ba-Bi liquid, in which associates have been assumed in existing thermodynamic modeling. It is found that in the Ba rich melt, the Bi atoms are almost completely surrounded by Ba atoms. The Bi-centered coordination polyhedrons are strongly associated to crystalline structures of Ba5Bi3 and Ba4Bi3 with a longer lifetime than other polyhedrons during the AIMD simulations. In addition, these Bi-centered polyhedrons in Ba rich melt connect with each other through vertex, edge, face, and/or bipyramid sharing to form medium range orders (MRO). In the Bi rich melt, the Ba-centered polyhedrons also form MROs, but they are both structurally and compositionally diverse with a shorter lifetime. These findings from AIMD study provide evidences that there exist a strongly ordering Ba4Bi3 associate and a weakly ordering BaBi3 associate in the Ba-Bi liquid. The predicted enthalpy of mixing in the liquid agrees well with the results by the CALPHAD modeling in the literature.

cond-mat.mtrl-sci↗