Related papers: Analyzing Speaker Information in Self-Supervised M…
The accuracy of automated speaker recognition is negatively impacted by change in emotions in a person's speech. In this paper, we hypothesize that speaker identity is composed of various vocal style factors that may be learned from…
This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…
Cross-modal noise-robust learning is a challenging task since noisy correspondence is hard to recognize and rectify. Due to the cumulative and unavoidable negative impact of unresolved noise, existing methods cannot maintain a stable…
Recent advances in unsupervised speech representation learning discover new approaches and provide new state-of-the-art for diverse types of speech processing tasks. This paper presents an investigation of using wav2vec 2.0 deep speech…
Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…
An important step in speaker verification is extracting features that best characterize the speaker voice. This paper investigates a front-end processing that aims at improving the performance of speaker verification based on the SVMs…
Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been extensively investigated in the supervised setting. This assumes the existence of a parallel corpus of speech and orthographic transcriptions. Recently,…
Standard fine-tuning of pre-trained audio models couples representation learning with classifier training, which can obscure the true quality of the learned representations. In this work, we advocate for a disentangled two-stage framework…
Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal data. Speaker anonymization aims to remove speaker information…
Speaker recognition is a task of identifying persons from their voices. Recently, deep learning has dramatically revolutionized speaker recognition. However, there is lack of comprehensive reviews on the exciting progress. In this paper, we…
There is increasing interest in the use of the LEArnable Front-end (LEAF) in a variety of speech processing systems. However, there is a dearth of analyses of what is actually learnt and the relative importance of training the different…
Noisy labels are inevitable yet problematic in machine learning society. It ruins the generalization of a classifier by making the classifier over-fitted to noisy labels. Existing methods on noisy label have focused on modifying the…
The increasing level of sound pollution in marine environments poses an increased threat to ocean health, making it crucial to monitor underwater noise. By monitoring this noise, the sources responsible for this pollution can be mapped.…
In this paper, a novel method of designing a codebook for noise robust speaker identification purpose utilizing Genetic Algorithm has been proposed. Wiener filter has been used to remove the background noises from the source speech…
The most pressing challenge in the field of voice biometrics is selecting the most efficient technique of speaker recognition. Every individual's voice is peculiar, factors like physical differences in vocal organs, accent and pronunciation…
For sequence transduction tasks like speech recognition, a strong structured prior model encodes rich information about the target space, implicitly ruling out invalid sequences by assigning them low probability. In this work, we propose…
Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning is applied to voice conversion successfully based on speaker labels. However, the performance of model…
Zero-resource word segmentation and clustering systems aim to tokenise speech into word-like units without access to text labels. Despite progress, the induced lexicons are still far from perfect. In an idealised setting with gold word…
Speaker verification system trained on one domain usually suffers performance degradation when applied to another domain. To address this challenge, researchers commonly use feature distribution matching-based methods in unsupervised domain…
Preserving a patient's identity is a challenge for automatic, speech-based diagnosis of mental health disorders. In this paper, we address this issue by proposing adversarial disentanglement of depression characteristics and speaker…