Duo Ma

Jing Peng, Junhao Du, Chenghao Wang et al.

Speech foundation models and Speech LLMs have advanced speech understanding, yet deployment-oriented model selection is hindered by non-comparable evaluations caused by mismatched post-processing, and by training results that are hard to reproduce across data scales and pipelines. We present SURE, a unified experimentation framework that standardizes prediction formats, normalization, and scoring. SURE evaluates strong systems across paradigms, from conventional pipelines to Speech LLMs, on representative tasks under realistic acoustic and linguistic stressors. Beyond evaluation, SURE introduces an agent-assisted training conversion flow that maps paper and code into versioned, runnable training pipelines under a unified protocol on matched open-data subsets. Overall, SURE improves comparability and reproducibility for deployment-oriented evaluation.

Shengjun Zhu, Siyu Liu, Runqing Xiong et al.

Purpose: Prenatal ultrasound is a key tool in evaluating fetal structural development and detecting abnormalities, contributing to reduced perinatal complications and improved neonatal survival. Accurate identification of standard fetal torso planes is essential for reliable assessment and personalized prenatal care. However, limitations such as low contrast and unclear texture details in ultrasound imaging pose significant challenges for fine-grained anatomical recognition. Methods: We propose a novel Multi-Contrast Fusion Module (MCFM) to enhance the model's ability to extract detailed information from ultrasound images. MCFM operates exclusively on the lower layers of the neural network, directly processing raw ultrasound data. By assigning attention weights to image representations under different contrast conditions, the module enhances feature modeling while explicitly maintaining minimal parameter overhead. Results: The proposed MCFM was evaluated on a curated dataset of fetal torso plane ultrasound images. Experimental results demonstrate that MCFM substantially improves recognition performance, with a minimal increase in model complexity. The integration of multi-contrast attention enables the model to better capture subtle anatomical structures, contributing to higher classification accuracy and clinical reliability. Conclusions: Our method provides an effective solution for improving fetal torso plane recognition in ultrasound imaging. By enhancing feature representation through multi-contrast fusion, the proposed approach supports clinicians in achieving more accurate and consistent diagnoses, demonstrating strong potential for clinical adoption in prenatal screening. The codes are available at https://github.com/sysll/MCFM.

Jing Peng, Ziyi Chen, Haoyu Li et al.

We study timestamped speaker-attributed ASR for long-form, multi-party speech with overlap, where chunk-wise inference must preserve meeting-level speaker identity consistency while producing time-stamped, speaker-labeled transcripts. Previous Speech-LLM systems tend to prioritize either local diarization or global labeling, but often lack the ability to capture fine-grained temporal boundaries or robust cross-chunk identity linking. We propose G-STAR, an end-to-end system that couples a time-aware speaker-tracking module with a Speech-LLM transcription backbone. The tracker provides structured speaker cues with temporal grounding, and the LLM generates attributed text conditioned on these cues. G-STAR supports both component-wise optimization and joint end-to-end training, enabling flexible learning under heterogeneous supervision and domain shift. Experiments analyze cue fusion, local versus long-context trade-offs and hierarchical objectives.

Yang Qi, Jiaxin Cai, Jing Lu et al.

Prenatal ultrasound evaluates fetal growth and detects congenital abnormalities during pregnancy, but the examination of ultrasound images by radiologists requires expertise and sophisticated equipment, which would otherwise fail to improve the rate of identifying specific types of fetal central nervous system (CNS) abnormalities and result in unnecessary patient examinations. We construct a deep learning model to improve the overall accuracy of the diagnosis of fetal cranial anomalies to aid prenatal diagnosis. In our collected multi-center dataset of fetal craniocerebral anomalies covering four typical anomalies of the fetal central nervous system (CNS): anencephaly, encephalocele (including meningocele), holoprosencephaly, and rachischisis, patient-level prediction accuracy reaches 94.5%, with an AUROC value of 99.3%. In the subgroup analyzes, our model is applicable to the entire gestational period, with good identification of fetal anomaly types for any gestational period. Heatmaps superimposed on the ultrasound images not only provide a visual interpretation for the algorithm but also provide an intuitive visual aid to the physician by highlighting key areas that need to be reviewed, helping the physician to quickly identify and validate key areas. Finally, the retrospective reader study demonstrates that by combining the automatic prediction of the DL system with the professional judgment of the radiologist, the diagnostic accuracy and efficiency can be effectively improved and the misdiagnosis rate can be reduced, which has an important clinical application prospect.

Duo Ma, Nana Hou, Van Tung Pham et al.

To realize robust end-to-end Automatic Speech Recognition(E2E ASR) under radio communication condition, we propose a multitask-based method to joint train a Speech Enhancement (SE) module as the front-end and an E2E ASR model as the back-end in this paper. One of the advantage of the proposed method is that the entire system can be trained from scratch. Different from prior works, either component here doesn't need to perform pre-training and fine-tuning processes separately. Through analysis, we found that the success of the proposed method lies in the following aspects. Firstly, multitask learning is essential, that is the SE network is not only learning to produce more Intelligent speech, it is also aimed to generate speech that is beneficial to recognition. Secondly, we also found speech phase preserved from noisy speech is critical for improving ASR performance. Thirdly, we propose a dual channel data augmentation training method to obtain further improvement.Specifically, we combine the clean and enhanced speech to train the whole system. We evaluate the proposed method on the RATS English data set, achieving a relative WER reduction of 4.6% with the joint training method, and up to a relative WER reduction of 11.2% with the proposed data augmentation method.