相关论文: Self-supervised Pretraining for Robust Personalize…

Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…

Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity. This paper proposes an effective and parameter-efficient speaker…

We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by…

Recent self-supervision methods have found success in learning feature representations that could rival ones from full supervision, and have been shown to be beneficial to the model in several ways: for example improving models robustness…

State-of-the-art deep-learning-based voice activity detectors (VADs) are often trained with anechoic data. However, real acoustic environments are generally reverberant, which causes the performance to significantly deteriorate. To mitigate…

We compare self-supervised representation learning algorithms which either explicitly quantize the audio data or learn representations without quantization. We find the former to be more accurate since it builds a good vocabulary of the…

Speaker recognition performance has been greatly improved with the emergence of deep learning. Deep neural networks show the capacity to effectively deal with impacts of noise and reverberation, making them attractive to far-field speaker…

Recently proposed automatic pathological speech classification techniques use unsupervised auto-encoders to obtain a high-level abstract representation of speech. Since these representations are learned based on reconstructing the input,…

Speech models are often trained on sensitive data in order to improve model performance, leading to potential privacy leakage. Our work considers noise masking attacks, introduced by Amid et al. 2022, which attack automatic speech…

Speech quality assessment has been a critical issue in speech processing for decades. Existing automatic evaluations usually require clean references or parallel ground truth data, which is infeasible when the amount of data soars.…

Cross-lingual self-supervised learning has been a growing research topic in the last few years. However, current works only explored the use of audio signals to create representations. In this work, we study cross-lingual self-supervised…

Recent progress in speech recognition has relied on models trained on vast amounts of labeled data. However, classroom Automatic Speech Recognition (ASR) faces the real-world challenge of abundant weak transcripts paired with only a small…

We describe a novel weakly labeled Audio Event Classification approach based on a self-supervised attention model. The weakly labeled framework is used to eliminate the need for expensive data labeling procedure and self-supervised…

This work tackles Weakly Supervised Anomaly detection, in which a predictor is allowed to learn not only from normal examples but also from a few labeled anomalies made available during training. In particular, we deal with the localization…

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…

The task of making speaker verification systems robust to adverse scenarios remain a challenging and an active area of research. We developed an unsupervised feature enhancement approach in log-filter bank domain with the end goal of…

Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality distortions during image acquisition, transmission, or storage. While deep neural…

Recently, self-supervised pre-training has gained success in automatic speech recognition (ASR). However, considering the difference between speech accents in real scenarios, how to identify accents and use accent features to improve ASR is…

Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining…

Neural unsupervised parsing (UP) models learn to parse without access to syntactic annotations, while being optimized for another task like language modeling. In this work, we propose self-training for neural UP models: we leverage…