Related papers: Learning De-identified Representations of Prosody …

Lifelong audio feature extraction involves learning new sound classes incrementally, which is essential for adapting to new data distributions over time. However, optimizing the model only on new data can lead to catastrophic forgetting of…

An effective way to increase the noise robustness of automatic speech recognition is to label noisy speech features as either reliable or unreliable (missing) prior to decoding, and to replace the missing ones by clean speech estimates. We…

Textless self-supervised speech models have grown in capabilities in recent years, but the nature of the linguistic information they encode has not yet been thoroughly examined. We evaluate the extent to which these models' learned…

In this paper, we propose a novel prosody disentangle method for prosodic Text-to-Speech (TTS) model, which introduces the vector quantization (VQ) method to the auxiliary prosody encoder to obtain the decomposed prosody representations in…

Learning to understand grounded language, which connects natural language to percepts, is a critical research area. Prior work in grounded language acquisition has focused primarily on textual inputs. In this work we demonstrate the…

When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data…

We present an approach for unsupervised learning of speech representation disentangling contents and styles. Our model consists of: (1) a local encoder that captures per-frame information; (2) a global encoder that captures per-utterance…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…

When beginners learn to speak a non-native language, it is difficult for them to judge for themselves whether they are speaking well. Therefore, computer-assisted pronunciation training systems are used to detect learner mispronunciations.…

Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various data augmentation…

Faced with the threat of identity leakage during voice data publishing, users are engaged in a privacy-utility dilemma when enjoying convenient voice services. Existing studies employ direct modification or text-based re-synthesis to…

An accurate objective speech intelligibility prediction algorithms is of great interest for many applications such as speech enhancement for hearing aids. Most algorithms measures the signal-to-noise ratios or correlations between the…

Whispered speech is characterised by a noise-like excitation that results in the lack of fundamental frequency. Considering that prosodic phenomena such as intonation are perceived through f0 variation, the perception of whispered prosody…

We present a neural analysis and synthesis (NANSY) framework that can manipulate voice, pitch, and speed of an arbitrary speech signal. Most of the previous works have focused on using information bottleneck to disentangle analysis features…

Tools to generate high quality synthetic speech signal that is perceptually indistinguishable from speech recorded from human speakers are easily available. Several approaches have been proposed for detecting synthetic speech. Many of these…

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…

The prosodic aspects of speech signals produced by current text-to-speech systems are typically averaged over training material, and as such lack the variety and liveliness found in natural speech. To avoid monotony and averaged prosody…

As equality issues in the use of face recognition have garnered a lot of attention lately, greater efforts have been made to debiased deep learning models to improve fairness to minorities. However, there is still no clear definition nor…

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression objective but also…