相关论文: A Semi-Supervised Framework for Speech Confidence …

Recent state-of-the-art methods in semi-supervised learning (SSL) combine consistency regularization with confidence-based pseudo-labeling. To obtain high-quality pseudo-labels, a high confidence threshold is typically adopted. However, it…

In recent years, semi-supervised learning (SSL) has shown tremendous success in leveraging unlabeled data to improve the performance of deep learning models, which significantly reduces the demand for large amounts of labeled data. Many SSL…

This paper presents our system for the MISP-Meeting Challenge Track 2. The primary difficulty lies in the dataset, which contains strong background noise, reverberation, overlapping speech, and diverse meeting topics. To address these…

Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the…

We propose a semi-supervised text classifier based on self-training using one positive and one negative property of neural networks. One of the weaknesses of self-training is the semantic drift problem, where noisy pseudo-labels accumulate…

Self-supervised learning (SSL) has transformed speech processing, with benchmarks such as SUPERB establishing fair comparisons across diverse downstream tasks. Despite it's security-critical importance, Audio deepfake detection has remained…

Large-scale end-to-end models such as Whisper have shown strong performance on diverse speech tasks, but their internal behavior on pathological speech remains poorly understood. Understanding how dysarthric speech is represented across…

Recent studies have shown that pseudo labels can contribute to unsupervised domain adaptation (UDA) for speaker verification. Inspired by the self-training strategies that use an existing classifier to label the unlabeled data for…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

We propose a novel semi-supervised learning (SSL) method that adopts selective training with pseudo labels. In our method, we generate hard pseudo-labels and also estimate their confidence, which represents how likely each pseudo-label is…

Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.…

Many existing speaker verification systems are reported to be vulnerable against different spoofing attacks, for example speaker-adapted speech synthesis, voice conversion, play back, etc. In order to detect these spoofed speech signals as…

Self-supervised learning (SSL) based speech pre-training has attracted much attention for its capability of extracting rich representations learned from massive unlabeled data. On the other hand, the use of weakly-supervised data is less…

In recent years, the remarkable advancements in deep neural networks have brought tremendous convenience. However, the training process of a highly effective model necessitates a substantial quantity of samples, which brings huge potential…

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…

Detecting depression from social media text is still a challenging task. This is due to different language styles, informal expression, and the lack of annotated data in many languages. To tackle these issues, we propose, Semi-SMDNet, a…

This paper proposes a powerful Visual Speech Recognition (VSR) method for multiple languages, especially for low-resource languages that have a limited number of labeled data. Different from previous methods that tried to improve the VSR…

Speech Emotion Recognition (SER) application is frequently associated with privacy concerns as it often acquires and transmits speech data at the client-side to remote cloud platforms for further processing. These speech data can reveal not…

Weakly Supervised Sound Event Detection (WSSED), which relies on audio tags without precise onset and offset times, has become prevalent due to the scarcity of strongly labeled data that includes exact temporal boundaries for events. This…

Unsupervised person re-identification (re-ID) aims at learning discriminative representations for person retrieval from unlabeled data. Recent techniques accomplish this task by using pseudo-labels, but these labels are inherently noisy and…