Related papers: Improving Distortion Robustness of Self-supervised…

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server…

Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A common way to improve model robustness is adversarial training…

Benefiting from the development of deep learning, text-to-speech (TTS) techniques using clean speech have achieved significant performance improvements. The data collected from real scenes often contains noise and generally needs to be…

Speech emotion recognition (SER) has attracted great attention in recent years due to the high demand for emotionally intelligent speech interfaces. Deriving speaker-invariant representations for speech emotion recognition is crucial. In…

Speech enhancement deep learning systems usually require large amounts of training data to operate in broad conditions or real applications. This makes the adaptability of those systems into new, low resource environments an important…

In this paper we investigate the use of adversarial domain adaptation for addressing the problem of language mismatch between speaker recognition corpora. In the context of speaker verification, adversarial domain adaptation methods aim at…

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…

We investigate the performance of self-supervised pretraining frameworks on pathological speech datasets used for automatic speech recognition (ASR). Modern end-to-end models require thousands of hours of data to train well, but only a…

This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery…

Speaker diarization, which is to find the speech segments of specific speakers, has been widely used in human-centered applications such as video conferences or human-computer interaction systems. In this paper, we propose a self-supervised…

Data sparsity is an inherent challenge in the recommender systems, where most of the data is collected from the implicit feedbacks of users. This causes two difficulties in designing effective algorithms: first, the majority of users only…

This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models. We specifically address the few-shot learning scenario where access to…

Many people are suffering from voice disorders, which can adversely affect the quality of their lives. In response, some researchers have proposed algorithms for automatic assessment of these disorders, based on voice signals. However,…

Discourse analysis and discourse parsing have shown great impact on many important problems in the field of Natural Language Processing (NLP). Given the direct impact of discourse annotations on model performance and interpretability,…

This report presents the system developed by the ABSP Laboratory team for the third DIHARD speech diarization challenge. Our main contribution in this work is to develop a simple and efficient solution for acoustic domain dependent speech…

Adversarial Training (AT), which is commonly accepted as one of the most effective approaches defending against adversarial examples, can largely harm the standard performance, thus has limited usefulness on industrial-scale production and…

In recent Text-to-Speech (TTS) systems, a neural vocoder often generates speech samples by solely conditioning on acoustic features predicted from an acoustic model. However, there are always distortions existing in the predicted acoustic…

Human language is a combination of elemental languages/domains/styles that change across and sometimes within discourses. Language models, which play a crucial role in speech recognizers and machine translation systems, are particularly…

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…