Related papers: Adapting General Disentanglement-Based Speaker Ano…

Audio deepfake is so sophisticated that the lack of effective detection methods is fatal. While most detection systems primarily rely on low-level acoustic features or pretrained speech representations, they frequently neglect high-level…

Emotions play a central role in human communication, shaping trust, engagement, and social interaction. As artificial intelligence systems powered by large language models become increasingly integrated into everyday life, enabling them to…

Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging unlabelled utterances, due to the classification loss over training speakers. In this paper, we explore an alternative training strategy to enable the…

Domain adaptation aims to mitigate the domain gap when transferring knowledge from an existing labeled domain to a new domain. However, existing disentanglement-based methods do not fully consider separation between domain-invariant and…

Multimodal emotion recognition in conversations aims to infer utterance-level emotions by jointly modeling textual, acoustic, and visual cues within context. Despite recent progress, key challenges remain, including redundant cross-modal…

Recently end-to-end neural audio/speech coding has shown its great potential to outperform traditional signal analysis based audio codecs. This is mostly achieved by following the VQ-VAE paradigm where blind features are learned,…

Speaker recognition performance in emotional talking environments is not as high as it is in neutral talking environments. This work focuses on proposing, implementing, and evaluating a new approach to enhance the performance in emotional…

The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural…

The current trend in automatic speech recognition is to leverage large amounts of labeled data to train supervised neural network models. Unfortunately, obtaining data for a wide range of domains to train robust models can be costly.…

The temporal dynamics of speech, encompassing variations in rhythm, intonation, and speaking rate, contain important and unique information about speaker identity. This paper proposes a new method for representing speaker characteristics by…

We present a new approach to disentangle speaker voice and phone content by introducing new components to the VQ-VAE architecture for speech synthesis. The original VQ-VAE does not generalize well to unseen speakers or content. To alleviate…

Voice trigger detection is an important task, which enables activating a voice assistant when a target user speaks a keyword phrase. A detector is typically trained on speech data independent of speaker information and used for the voice…

Textless speech-to-speech translation systems are rapidly advancing, thanks to the integration of self-supervised learning techniques. However, existing state-of-the-art systems fall short when it comes to capturing and transferring…

Voice-enabled interactions provide more human-like experiences in many popular IoT systems. Cloud-based speech analysis services extract useful information from voice input using speech recognition techniques. The voice signal is a rich…

Speaker verification is a task of confirming an individual's identity through the analysis of their voice. Whispered speech differs from phonated speech in acoustic characteristics, which degrades the performance of speaker verification…

The goal of this contribution is to use a parametric speech synthesis system for reducing background noise and other interferences from recorded speech signals. In a first step, Hidden Markov Models of the synthesis system are trained. Two…

Speaker anonymization aims to conceal speaker-specific attributes in speech signals, making the anonymized speech unlinkable to the original speaker identity. Recent approaches achieve this by disentangling speech into content and speaker…

This study investigates the explainability of embedding representations, specifically those used in modern audio spoofing detection systems based on deep neural networks, known as spoof embeddings. Building on established work in speaker…

Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Recently, AutoVC, a conditional autoencoder based method, achieved excellent conversion results by disentangling the speaker identity…

Emotional voice conversion aims to transform emotional prosody in speech while preserving the linguistic content and speaker identity. Prior studies show that it is possible to disentangle emotional prosody using an encoder-decoder network…