相关论文: On Loss Functions for Supervised Monaural Time-Dom…

Recently, there has been significant progress made in Automatic Speech Recognition (ASR) of code-switched speech, leading to gains in accuracy on code-switched datasets in many language pairs. Code-switched speech co-occurs with monolingual…

In sequence prediction tasks like neural machine translation, training with cross-entropy loss often leads to models that overgeneralize and plunge into local optima. In this paper, we propose an extended loss function called \emph{dual…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

This paper proposes an unsupervised data selection method by using a submodular function based on contrastive loss ratios of target and training data sets. A model using a contrastive loss function is trained on both sets. Then the ratio of…

Unsupervised monocular depth learning generally relies on the photometric relation among temporally adjacent images. Most of previous works use both mean absolute error (MAE) and structure similarity index measure (SSIM) with conventional…

The use of spatial information with multiple microphones can improve far-field automatic speech recognition (ASR) accuracy. However, conventional microphone array techniques degrade speech enhancement performance when there is an array…

Sound matching algorithms seek to approximate a target waveform by parametric audio synthesis. Deep neural networks have achieved promising results in matching sustained harmonic tones. However, the task is more challenging when targets are…

Feature mapping using deep neural networks is an effective approach for single-channel speech enhancement. Noisy features are transformed to the enhanced ones through a mapping network and the mean square errors between the enhanced and…

While supervised quality predictors for synthesized speech have demonstrated strong correlations with human ratings, their requirement for in-domain labeled training data hinders their generalization ability to new domains. Unsupervised…

In this work, we study the features extracted by English self-supervised learning (SSL) models in cross-lingual contexts and propose a new metric to predict the quality of feature representations. Using automatic speech recognition (ASR) as…

Robust voice activity detection (VAD) is a challenging task in low signal-to-noise (SNR) environments. Recent studies show that speech enhancement is helpful to VAD, but the performance improvement is limited. To address this issue, here we…

Distribution system state estimation (DSSE) plays a crucial role in the real-time monitoring, control, and operation of distribution networks. Besides intensive computational requirements, conventional DSSE methods need high-quality…

Automatic speech recognition (ASR) has gained remarkable successes thanks to recent advances of deep learning, but it usually degrades significantly under real-world noisy conditions. Recent works introduce speech enhancement (SE) as…

In self-supervised learning, it is challenging to reduce the gap between the enhancement performance on the estimated and target speech signals with existed pre-tasks. In this paper, we propose a multi-task pre-training method to improve…

Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. This paper aims to address this problem by revisiting the…

The speaker extraction algorithm extracts the target speech from a mixture speech containing interference speech and background noise. The extraction process sometimes over-suppresses the extracted target speech, which not only creates…

Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned super-resolution.…

Although generation-based dialogue systems have been widely researched, the response generations by most existing systems have very low diversities. The most likely reason for this problem is Maximum Likelihood Estimation (MLE) with Softmax…

Deep learning models have become an increasingly preferred option for biometric recognition systems, such as speaker recognition. SincNet, a deep neural network architecture, gained popularity in speaker recognition tasks due to its…

Self-supervised speech representation learning has recently been a prosperous research topic. Many algorithms have been proposed for learning useful representations from large-scale unlabeled data, and their applications to a wide range of…