Automatic speech quality assessment has raised more attention as an alternative or support to traditional perceptual clinical evaluation. However, most research so far only gains good results on simple tasks such as binary classification, largely due to data scarcity. To deal with this challenge, current works tend to segment patients' audio files into many samples to augment the datasets. Nevertheless, this approach has limitations, as it indirectly relates overall audio scores to individual segments. This paper introduces a novel approach where the system learns at the audio level instead of segments despite data scarcity. This paper proposes to use the pre-trained Wav2Vec2 architecture for both SSL, and ASR as feature extractor in speech assessment. Carried out on the HNC dataset, our ASR-driven approach established a new baseline compared with other approaches, obtaining average $MSE=0.73$ and $MSE=1.15$ for the prediction of intelligibility and severity scores respectively, using only 95 training samples. It shows that the ASR based Wav2Vec2 model brings the best results and may indicate a strong correlation between ASR and speech quality assessment. We also measure its ability on variable segment durations and speech content, exploring factors influencing its decision.
From Statistical Methods to Pre-Trained Models; A Survey on Automatic Speech Recognition for Resource Scarce Urdu Language
Shenzhen University（深圳大学）；School of Artificial Intelligence, CAS Institute of Automation（中国科学院自动化研究所人工智能学院）；University of Chinese Academy of Sciences（中国科学院大学）
VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining
School of Computer Science, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, shanghai innovation instituteChina Tencent AI LabUSA（计算机科学学院、人工智能国家重点实验室、上海交通大学、上海创新研究院中国腾讯AI实验室美国）
Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data
The University of Tokyo（东京大学）；Japan National Institute of Advanced Industrial Science and Technology (AIST)（日本国家工业科学与技术研究院）；Japan Kyoto University（京都大学）
TG-ASR: Translation-Guided Learning with Parallel Gated Cross Attention for Low-Resource Automatic Speech Recognition
Dept. Computer Science and Information Engineering, National Taiwan Normal University, Taiwan（计算机科学与信息工程系，台湾国立台湾师范大学）；Institute of Computer Science, Academia Sinica, Taiwan（学术院计算机科学研究所，台湾）；United Link Co., Ltd., Taiwan（台湾联合链接有限公司）
Controllable Dysarthric Speech Synthesis with Patient-Specific Conditioning for Speaker-Diverse ASR Augmentation
Department of Language Science and Technology, The Hong Kong Polytechnic University（语言科学与技术系，香港理工大学）；College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine（康复医学学院，福建中医药大学）；Department of Imaging, Rehabilitation Hospital affiliated to Fujian University of Traditional Chinese Medicine（影像科，福建中医药大学附属康复医院）
A Wav2vec2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition
University of Galway（戈尔韦大学）；University Politehnica of Bucharest（布加勒斯特理工大学）
尽管最近深度学习技术取得了进步，但儿童语音识别仍然是一项具有挑战性的任务。当前的自动语音识别（ASR）模型需要大量的注释数据用于训练，这是稀缺的。在这项工作中，我们探索使用ASR模型，wav2vec2，不同的预训练和微调配置的自我监督学习（SSL），以提高自动儿童语音识别。使用不同数量的儿童语音训练数据、成人语音数据以及两者的组合对预训练的wav2vec2模型进行微调，以发现微调儿童ASR任务模型所需的最佳数据量。与任何其他以前的方法相比，我们训练的模型在MyST儿童语音数据集上实现了7.42的最佳单词错误率（WER），在PFSTAR数据集上实现了2.99，在CMU KIDS数据集上实现了12.47。我们的模型在儿童语音上的表现优于wav2vec2 BASE 960，后者被认为是最先进的成人语音ASR模型，仅使用10小时的儿童语音数据进行微调。还通过在预训练、微调和推理中使用数据集的组合来分析不同类型的训练数据及其对推理的影响。
DENT-DDSP: Data-efficient noisy speech generator using differentiable digital signal processors for explicit distortion modelling and noise-robust speech recognition
GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement
X-LANCE Lab, SCS, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University（X-LANCE实验室、SCS、人工智能MoE重点实验室、上海交通大学）；Pengcheng Laboratory（鹏城实验室）；The Chinese University of Hong Kong（香港中文大学）；Dept EE, Tsinghua University（清华大学电子工程系）；SII；Harbin Institute of Technology（哈尔滨工业大学）；Birch AI；Dataocean AI；AISpeech Ltd（AISpeech有限公司）；Seasalt AI Inc（Seasalt AI公司）；SpeechColab
Grammar Based Speaker Role Identification for Air Traffic Control Speech Recognition
Idiap Research Institute（Idiap研究所）；Brno University of Technology（布尔诺理工大学）；Ecole Polytechnique Federale de Lausanne (EPFL)（洛桑联邦理工学院）；University of Zurich（苏黎世大学）；German Aerospace Center (DLR)（德国航空航天中心）
Efficient acoustic feature transformation in mismatched environments using a Guided-GAN
North-West University（西北大学）；Centre for Artificial Intelligence Research（人工智能研究中心）；National Institute for Theoretical and Computational Sciences（国家理论与计算科学研究所）；Saigen（Saigen公司）
NUVA: A Naming Utterance Verifier for Aphasia Treatment
University College London（伦敦大学学院）；SoftV（SoftV公司）；Goldsmiths College, University of London（伦敦大学金史密斯学院）
失名症（找词困难）是失语症的标志，失语症是一种获得性语言障碍，最常见的原因是中风。使用图片命名任务评估言语表现是诊断和监测失语症（PWA）患者对治疗干预反应的关键方法。目前，这种评估是由言语和语言治疗师（speech and language therapists，简称spr）手动进行的。令人惊讶的是，尽管自动语音识别（ASR）和人工智能与深度学习等技术取得了进步，但为这项任务开发自动化系统的研究却很少。在这里，我们提出了NUVA，一个话语验证系统，结合了深度学习元素，分类“正确”与“不正确”的命名尝试从失语症中风患者。当对八名母语为英国英语的PWA进行测试时，该系统的性能准确度范围在83.6%至93.6%之间，10倍交叉验证平均值为89.5%。这一表现不仅显著优于使用领先的商业可用ASR（谷歌语音转文本服务）为本研究创建的基线，而且在某些情况下与同一数据集的两个独立的语音评级相当。
Deterministic Prompting for Speaker-Stable Low-Resource Greek TTS
Institute for Language and Speech Processing, Athena R.C.（雅典娜研究与创新中心语言与语音处理研究所）；Department of Digital Medicine, University of Bern（伯尔尼大学数字医学系）；School of Electrical and Computer Engineering, National Technical University of Athens（雅典国家技术大学电气与计算机工程学院）
Normal-Anchored First-Order Model-Agnostic Meta-Learning based Whisper Fine-Tuning for Enhancing Fairness of Cleft Lip and Palate Speech Recognition
Indian Institute of Technology Guwahati（印度古瓦哈蒂印度理工学院）；University of Eastern Finland（东芬兰大学）；Brigham and Women's Hospital, Harvard Medical School（哈佛医学院布莱根妇女医院）；Indian Institute of Information Technology Dharwad (IIIT Dharwad)（达尔瓦德印度信息技术学院（IIIT达尔瓦德））
Gated Multi-Graph Fusion via Graph Attention Networks for Alzheimer's Disease Detection
School of Future Technology, Tianjin University（天津大学未来技术学院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；College of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院）；Huiyan Technology (Tianjin) Co., Ltd（慧眼科技（天津）有限公司）
