TMS: A Temporal Multi-scale Backbone Design for Speaker Embedding
Tianjin University（天津大学）；Qinghai Nationalities University（青海民族大学）；National Institute of Information and Communications Technology（国立信息通信技术研究所）；National Institute of Informatics（国立信息学研究所）；Xi’an Jiaotong University（西安交通大学）
Ruiteng Zhang, Jianguo Wei, Xugang Lu, Wenhuan Lu, Di Jin, Junhai Xu, Lin Zhang, Yantao Ji, Jianwu Dang
备注：
Due to the limitation "The abstract field cannot be longer than 1,920 characters", the abstract here is shorter than that in the PDF file
Speaker embedding is an important front-end module to explore discriminative speaker features for many speech applications where speaker information is needed. Current SOTA backbone networks for speaker embedding are designed to aggregate multi-scale features from an utterance with multi-branch network architectures for speaker representation. However, naively adding many branches of multi-scale features with the simple fully convolutional operation could not efficiently improve the performance due to the rapid increase of model parameters and computational complexity. Therefore, in the most current state-of-the-art network architectures, only a few branches corresponding to a limited number of temporal scales could be designed for speaker embeddings. To address this problem, in this paper, we propose an effective temporal multi-scale (TMS) model where multi-scale branches could be efficiently designed in a speaker embedding network almost without increasing computational costs. The new model is based on the conventional TDNN, where the network architecture is smartly separated into two modeling operators: a channel-modeling operator and a temporal multi-branch modeling operator. Adding temporal multi-scale in the temporal multi-branch operator needs only a little bit increase of the number of parameters, and thus save more computational budget for adding more branches with large temporal scales. Moreover, in the inference stage, we further developed a systemic re-parameterization method to convert the TMS-based model into a single-path-based topology in order to increase inference speed. We investigated the performance of the new TMS method for automatic speaker verification (ASV) on in-domain and out-of-domain conditions. Results show that the TMS-based model obtained a significant increase in the performance over the SOTA ASV models, meanwhile, had a faster inference speed.
CS-Rep: Making Speaker Verification Networks Embracing Re-parameterization
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学院）；Computer College, Qinghai Nationalities University（青海民族大学计算机学院）；National Institute of Informatics（日本国立信息学研究所）；School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件工程学院）；National Institute of Information and Communications Technology（日本国立信息与通信技术研究所）
Dialogue-Based Streaming Audio-Visual Target Speaker Extraction with Predictive Dialogue Information
Shenzhen Loop Area Institute（深圳河套学院）；School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）人工智能学院）；The Chinese University of Hong Kong（香港中文大学）
P-vectors: A Parallel-Coupled TDNN/Transformer Network for Speaker Verification
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Future Technology（未来技术学院）；University of Chinese Academy of Sciences（中国科学院大学）；GammaLab, PingAn OneConnect（平安壹账通Gamma实验室）；PingAn Insurance (Group) Company of China（中国平安保险（集团）股份有限公司）
HELIX: Scaling Raw Audio Understanding with Hybrid Mamba-Attention Beyond the Quadratic Limit
Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany（弗赖堡大学计算机科学系，德国弗赖堡市）；Department of Computer Engineering（计算机工程系）；Information Technology, Veermata Jijabai Technological Institute, Mumbai, India（维尔玛塔·吉贾拜技术学院信息科技系，印度孟买）
Synthetic Speech Source Tracing using Metric Learning
Athens University of Economics and Business（雅典经济与商业大学）；National and Kapodistrian University of Athens（雅典国家与卡布里亚大学）；Omilia - Conversational Intelligence（Omilia-对话智能）
Task-Vector Arithmetic for Emotional Expressivity Control in Language-Model-Based Text-to-Speech
Instituto de Biociências, Letras e Ciências Exatas Universidade Estadual Paulista "Júlio de Mesquita Filho" (UNESP)（生物科学、文学和精确科学学院 帕尔马斯州立大学 "Júlio de Mesquita Filho" (UNESP)）
