Related papers: Reimagining Speech: A Scoping Review of Deep Learn…
Expressive voice conversion (VC) conducts speaker identity conversion for emotional speakers by jointly converting speaker identity and emotional style. Emotional style modeling for arbitrary speakers in expressive VC has not been…
Voice conversion (VC) refers to transforming the speaker characteristics of an utterance without altering its linguistic contents. Many works on voice conversion require to have parallel training data that is highly expensive to acquire.…
Non-parallel voice conversion (VC) is typically achieved using lossy representations of the source speech. However, ensuring only speaker identity information is dropped whilst all other information from the source speech is retained is a…
Voice conversion has gained increasing popularity in many applications of speech synthesis. The idea is to change the voice identity from one speaker into another while keeping the linguistic content unchanged. Many voice conversion…
Inspired by the humans' cognitive ability to generalise knowledge and skills, Self-Supervised Learning (SSL) targets at discovering general representations from large-scale data without requiring human annotations, which is an expensive and…
Machine reading comprehension is a challenging task and hot topic in natural language processing. Its goal is to develop systems to answer the questions regarding a given context. In this paper, we present a comprehensive survey on…
Audio-visual correlation learning aims to capture and understand natural phenomena between audio and visual data. The rapid growth of Deep Learning propelled the development of proposals that process audio-visual data and can be observed in…
Brain signals accompany various information relevant to human actions and mental imagery, making them crucial to interpreting and understanding human intentions. Brain-computer interface technology leverages this brain activity to generate…
This paper proposes a voice conversion (VC) method based on a sequence-to-sequence (S2S) learning framework, which enables simultaneous conversion of the voice characteristics, pitch contour, and duration of input speech. We previously…
Most state-of-the-art speech systems are using Deep Neural Networks (DNNs). Those systems require a large amount of data to be learned. Hence, learning state-of-the-art frameworks on under-resourced speech languages/problems is a difficult…
With its crosslinguistic and cross-speaker diversity, the Mozilla Common Voice Corpus (CV) has been a valuable resource for multilingual speech technology and holds tremendous potential for research in crosslinguistic phonetics and speech…
Recent progress in generative AI has made it increasingly easy to create natural-sounding deepfake speech from just a few seconds of audio. While these tools support helpful applications, they also raise serious concerns by making it…
Singing Voice Synthesis (SVS) has witnessed significant advancements with the advent of deep learning techniques. However, a significant challenge in SVS is the scarcity of labeled singing voice data, which limits the effectiveness of…
With the advent of general-purpose speech representations from large-scale self-supervised models, applying a single model to multiple downstream tasks is becoming a de-facto approach. However, the pooling problem remains; the length of…
Objective. When a person listens to continuous speech, a corresponding response is elicited in the brain and can be recorded using electroencephalography (EEG). Linear models are presently used to relate the EEG recording to the…
Voice conversion for highly expressive speech is challenging. Current approaches struggle with the balancing between speaker similarity, intelligibility and expressiveness. To address this problem, we propose Expressive-VC, a novel…
Our ability to comprehend speech remains, to date, unrivaled by deep learning models. This feat could result from the brain's ability to fine-tune generic sound representations for speech-specific processes. To test this hypothesis, we…
Sound sources localization using multichannel signal processing has been a subject of active research for decades. In recent years, the use of deep learning in audio signal processing has allowed to drastically improve performances for…
We generalized a voice morphing algorithm capable of handling temporally variable, multiple-attributes, and multiple instances. The generalized morphing provides a new strategy for investigating speech diversity. However, excessive…
Virtual assistants are becoming increasingly important speech-driven Information Retrieval platforms that assist users with various tasks. We discuss open problems and challenges with respect to modeling spoken information queries for…