相关论文: Batch-normalized joint training for DNN-based dist…

In this paper, we explore an improved framework to train a monoaural neural enhancement model for robust speech recognition. The designed training framework extends the existing mixture invariant training criterion to exploit both unpaired…

A speaker cluster-based speaker adaptive training (SAT) method under deep neural network-hidden Markov model (DNN-HMM) framework is presented in this paper. During training, speakers that are acoustically adjacent to each other are…

Deep learning-based speech enhancement has shown unprecedented performance in recent years. The most popular mono speech enhancement frameworks are end-to-end networks mapping the noisy mixture into an estimate of the clean speech. With…

Computational modeling of naturalistic conversations in clinical applications has seen growing interest in the past decade. An important use-case involves child-adult interactions within the autism diagnosis and intervention domain. In this…

This paper presents a theoretical analysis and practical evaluation of the main bottlenecks towards a scalable distributed solution for the training of Deep Neuronal Networks (DNNs). The presented results show, that the current state of the…

In spite of the popularity of end-to-end diarization systems nowadays, modular systems comprised of voice activity detection (VAD), speaker embedding extraction plus clustering, and overlapped speech detection (OSD) plus handling still…

Current deep neural network (DNN) based speech separation faces a fundamental challenge -- while the models need to be trained on short segments due to computational constraints, real-world applications typically require processing…

The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting. We propose a unified optimization framework for…

Single-channel speech separation is a crucial task for enhancing speech recognition systems in multi-speaker environments. This paper investigates the robustness of state-of-the-art Neural Network models in scenarios where the pitch…

Deep neural networks (DNNs) must cater to a variety of users with different performance needs and budgets, leading to the costly practice of training, storing, and maintaining numerous user/task-specific models. There are solutions in the…

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…

Automatic speech recognition models require large amounts of speech recordings for training. However, the collection of such data often is cumbersome and leads to privacy concerns. Federated learning has been widely used as an effective…

This paper presents a challenge to the community: given a large corpus of written text aligned to its normalized spoken form, train an RNN to learn the correct normalization function. We present a data set of general text where the…

Training task in classical machine learning models, such as deep neural networks, is generally implemented at a remote cloud center for centralized learning, which is typically time-consuming and resource-hungry. It also incurs serious…

Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data distributions. In this paper, we demonstrate properly…

Most of the current deep learning-based approaches for speech enhancement only operate in the spectrogram or waveform domain. Although a cross-domain transformer combining waveform- and spectrogram-domain inputs has been proposed, its…

Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications. This paper reviews and comments on the past,…

Batch Normalization (BatchNorm) is a widely adopted technique that enables faster and more stable training of deep neural networks (DNNs). Despite its pervasiveness, the exact reasons for BatchNorm's effectiveness are still poorly…

Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on tackling distant speech recognition as a separate problem,…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…