Voice activity detection is an essential pre-processing component for speech-related tasks such as automatic speech recognition (ASR). Traditional supervised VAD systems obtain frame-level labels from an ASR pipeline by using, e.g., a Hidden Markov model. These ASR models are commonly trained on clean and fully transcribed data, limiting VAD systems to be trained on clean or synthetically noised datasets. Therefore, a major challenge for supervised VAD systems is their generalization towards noisy, real-world data. This work proposes a data-driven teacher-student approach for VAD, which utilizes vast and unconstrained audio data for training. Unlike previous approaches, only weak labels during teacher training are required, enabling the utilization of any real-world, potentially noisy dataset. Our approach firstly trains a teacher model on a source dataset (Audioset) using clip-level supervision. After training, the teacher provides frame-level guidance to a student model on an unlabeled, target dataset. A multitude of student models trained on mid- to large-sized datasets are investigated (Audioset, Voxceleb, NIST SRE). Our approach is then respectively evaluated on clean, artificially noised, and real-world data. We observe significant performance gains in artificially noised and real-world scenarios. Lastly, we compare our approach against other unsupervised and supervised VAD methods, demonstrating our method's superiority.
Speaker detection in the wild: Lessons learned from JSALT 2019
The Johns Hopkins University（约翰斯·霍普金斯大学）；LIMSI, CNRS, Univ. Paris-Sud, Université Paris-Saclay（LIMSI、法国国家科学研究中心、巴黎第十一大学、巴黎萨克雷大学）；University of Science and Technology of China（中国科学技术大学）；SRI International（SRI国际公司）；ENS/INRIA/PSL, PSL Research University（巴黎高等师范学院/法国国家信息与自动化研究所/巴黎文理研究大学、巴黎文理研究大学）；ENS/CNRS/EHESS/INRIA/PSL, PSL Research University（巴黎高等师范学院/法国国家科学研究中心/高等社会科学研究学院/法国国家信息与自动化研究所/巴黎文理研究大学、巴黎文理研究大学）；École de Technologie Supérieure, Université du Québec（魁北克大学高等技术学院）；NEC Corporation（日本电气公司）；Rice University（莱斯大学）；University of California, San Diego（加利福尼亚大学圣迭戈分校）
VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks
Institut national de la recherche scientifique (INRS-EMT), Université du Québec（魁北克大学国家科学研究院（INRS-EMT））；INRS-UQO Mixed Research Unit on Cybersecurity（INRS-UQO网络安全联合研究单位）
Better Spanish Emotion Recognition In-the-wild: Bringing Attention to Deep Spectrum Voice Analysis
eHealth Center, Faculty of Computer Science, Multimedia；Telecommunicactions, Universitat Oberta de Catalunya, 08016 Barcelona, Spain , MIND/IN2UB, Department of Electronic；Biomedical Engineeering, Universitat de Barcelona, 08028 Barcelona, Spain
Teacher-Student Training for Robust Tacotron-based TTS
Inner Mongolia University（内蒙古大学）；National University of Singapore（新加坡国立大学）；University of Bremen（不来梅大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Look Who's Talking: Active Speaker Detection in the Wild
Yonsei University（延世大学）
在这项工作中，我们提出了一种新的视听数据集在野外主动扬声器检测。当一个说话者的脸是可见的，同时声音也是可听到的时，他或她就被认为是活跃的。虽然主动说话人检测是许多视听任务的关键预处理步骤，但没有现有的自然人类语音数据集来评估主动说话人检测的性能。因此，我们策划了Active Speakers in the Wild（ASW）数据集，其中包含视频和具有密集语音活动标签的共现语音片段。音频片段的视频和时间戳是从VoxConverse中解析和采用的，VoxConverse是一个现有的扬声器diarisation数据集，由野生视频组成。从视频中提取人脸轨迹，并以半自动的方式基于VoxConverse的时间戳对活动片段进行注释。两个参考系统，一个自我监督的系统和一个完全监督的，在数据集上进行评估，以提供ASW的基线性能。跨域评估是为了显示配音视频在训练数据中的负面影响而进行的。
ML-ITW: A Multilingual in-the-wild Benchmark for Speech Deepfake Detection
School of Cyber Science and Engineering, Wuhan University（武汉大学网络科学与工程学院）；Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education（教育部航天信息安全与可信计算重点实验室）
AnyEdit: A Unified Framework for Speech and Singing Voice Editing with Real-World Environmental Consistency
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Institute of Media Technology and Experience Design, Huawei（华为媒体技术与体验设计研究院）；City University of Macau（澳门城市大学）；Amphion Technology Co., Ltd.（声智科技有限公司）
