Related papers: Unsupervised Cross-Lingual Speech Emotion Recognit…
A pre-trained language model, BERT, has brought significant performance improvements across a range of natural language processing tasks. Since the model is trained on a large corpus of diverse topics, it shows robust performance for domain…
Automatically assessing emotional valence in human speech has historically been a difficult task for machine learning algorithms. The subtle changes in the voice of the speaker that are indicative of positive or negative emotional states…
Cross-corpus speech emotion recognition (SER) aims to transfer emotional knowledge from a labeled source corpus to an unlabeled corpus. However, prior methods require access to source data during adaptation, which is unattainable in…
Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of…
End-to-end automatic speech recognition (ASR) can achieve promising performance with large-scale training data. However, it is known that domain mismatch between training and testing data often leads to a degradation of recognition…
Domain adaptation (DA) is transfer learning which aims to learn an effective predictor on target data from source data despite data distribution mismatch between source and target. We present in this paper a novel unsupervised DA method for…
Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the…
In this paper, we propose a new unsupervised domain adaptation (DA) method called layer-adapted implicit distribution alignment networks (LIDAN) to address the challenge of cross-corpus speech emotion recognition (SER). LIDAN extends our…
Bringing empathy to a computerized system could significantly improve the quality of human-computer communications, as soon as machines would be able to understand customer intentions and better serve their needs. According to different…
Deep neural networks excel at learning from labeled data and achieve state-of-the-art resultson a wide array of Natural Language Processing tasks. In contrast, learning from unlabeled data, especially under domain shift, remains a…
Thanks to large-scale labeled training data, deep neural networks (DNNs) have obtained remarkable success in many vision and multimedia tasks. However, because of the presence of domain shift, the learned knowledge of the well-trained DNNs…
Signal classification models based on deep neural networks are typically trained on datasets collected under controlled conditions, either simulated or over-the-air (OTA), which are constrained to specific channel environments with limited…
The use of ML in engineering has grown steadily to support a wide array of applications. Among these methods, deep neural networks have been widely adopted due to their performance and accessibility, but they require large, high-quality…
Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can greatly increase the…
Deep neural network based speech enhancement approaches aim to learn a noisy-to-clean transformation using a supervised learning paradigm. However, such a trained-well transformation is vulnerable to unseen noises that are not included in…
This paper proposes a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN), which uses the domain-collaborative and domain-adversarial learning strategy for training the neural network. The…
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods due to the lack of annotated sequence data in many domains.…
Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains…
Research on Speech Emotion Recognition (SER) often faces challenges such as the lack of large-scale public datasets and limited generalization capability when dealing with data from different distributions. To solve this problem, this paper…
We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation. Unlike many earlier methods that rely on adversarial learning for feature alignment, we leverage contrastive learning to bridge…