Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy speech from the test-time user, a personalized speech enhancement model can be trained using self-supervised learning. One straightforward approach to model personalization is to use the target speaker's noisy recordings as pseudo-sources. Then, a pseudo denoising model learns to remove injected training noises and recover the pseudo-sources. However, this approach is volatile as it depends on the quality of the pseudo-sources, which may be too noisy. As a remedy, we propose an improvement to the self-supervised approach through data purification. We first train an SNR predictor model to estimate the frame-by-frame SNR of the pseudo-sources. Then, the predictor's estimates are converted into weights which adjust the frame-by-frame contribution of the pseudo-sources towards training the personalized model. We empirically show that the proposed data purification step improves the usability of the speaker-specific noisy data in the context of personalized speech enhancement. Without relying on any clean speech recordings or speaker embeddings, our approach may be seen as privacy-preserving.
The Hong Kong Polytechnic University（香港理工大学）；Texas A&M University（德州农工大学）
Graph contrastive learning (GCL) has emerged as an effective tool for learning unsupervised representations of graphs. The key idea is to maximize the agreement between two augmented views of each graph via data augmentation. Existing GCL models mainly focus on applying \textit{identical augmentation strategies} for all graphs within a given scenario. However, real-world graphs are often not monomorphic but abstractions of diverse natures. Even within the same scenario (e.g., macromolecules and online communities), different graphs might need diverse augmentations to perform effective GCL. Thu…
In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies the type of enhancement output. To improve the quality of the enhanced output and mitigate oversuppression, we experiment with re-weighting frames by the presence or absence of speech activity and applying augmentations to speaker embeddings. By training under a multi-task learning setting, we empirically show that the proposed unified model obtains promisin…
Renmin University of China（中国人民大学）；University of Montreal（蒙特利尔大学）
Personalized chatbots focus on endowing the chatbots with a consistent personality to behave like real users and further act as personal assistants. Previous studies have explored generating implicit user profiles from the user's dialogue history for building personalized chatbots. However, these studies only use the response generation loss to train the entire model, thus it is prone to suffer from the problem of data sparsity. Besides, they overemphasize the final generated response's quality while ignoring the correlations and fusions between the user's dialogue history, leading to rough da…
Indiana University, Luddy School of Informatics, Computing, and Engineering（印第安纳大学卢迪信息、计算与工程学院）
With the advances in deep learning, speech enhancement systems benefited from large neural network architectures and achieved state-of-the-art quality. However, speaker-agnostic methods are not always desirable, both in terms of quality and their complexity, when they are to be used in a resource-constrained environment. One promising way is personalized speech enhancement (PSE), which is a smaller and easier speech enhancement problem for small models to solve, because it focuses on a particular test-time user. To achieve the personalization goal, while dealing with the typical lack of person…
Georgia Institute of Technology（佐治亚理工学院）；Adobe Research（Adobe研究院）
How can we predict missing values in multi-dimensional data (or tensors) more accurately? The task of tensor completion is crucial in many applications such as personalized recommendation, image and video restoration, and link prediction in social networks. Many tensor factorization and neural network-based tensor completion algorithms have been developed to predict missing entries in partially observed tensors. However, they can produce inaccurate estimations as real-world tensors are very sparse, and these methods tend to overfit on the small amount of data. Here, we overcome these shortcomi…
Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Indiana University（印第安纳大学）；University of Maryland（马里兰大学）；Google Research（谷歌研究院）；Amazon Lab126（亚马逊Lab126）；Reykjavik University（雷克雅未克大学）
VecAug: Unveiling Camouflaged Frauds with Cohort Augmentation for Enhanced Detection
National University of Singapore（新加坡国立大学）；Shopee Singapore（Shopee新加坡）；Zhejiang University（浙江大学）；University of Michigan（密歇根大学）；Beijing Institute of Technology（北京理工大学）
The Chinese University of Hong Kong（香港中文大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large quantities of impaired speech required for ASR system development. This paper presents novel variational auto-encoder generative adversarial network (VAE-GAN) based personalized disordered speech augmentation approaches that simultaneously learn to encode, generate and discriminate synthesized impaired speech. Separate latent features are derived to learn dysarthric speec…
Subjective quality evaluation of personalized own voice reconstruction systems
Fraunhofer Institute for Digital Media Technology IDMT, Oldenburg Branch for Hearing, Speech and Audio Technology HSA, Germany（弗劳恩霍夫数字媒体技术研究所IDMT，奥尔登堡听力、语音和音频技术分部HSA，德国）；Carl von Ossietzky Universität Oldenburg, Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, Germany（卡尔·冯·奥西特茨基大学奥尔登堡分校，医学物理与声学系及卓越中心Hearing4all，德国）
With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. Researchers and industry prefer to use end-to-end ASR systems for on-device speech recognition tasks. This is because end-to-end systems can be made resource-efficient while maintaining a higher quality compared to hybrid systems. However, building end-to-end models requires a significant amount of speech data. Another challenging task associated with speech assistants is personalization, which mainly lies in handling out-of-vocabulary (O…
