Related papers: SNAP: Speaker Nulling for Artifact Projection in S…

Transient loud intrusions, often occurring in noisy environments, can completely overpower speech signal and lead to an inevitable loss of information. While existing algorithms for noise suppression can yield impressive results, their…

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Speaker change detection is an important task in multi-party interactions such as meetings and conversations. In this paper, we address the speaker change detection task from the perspective of sequence transduction. Specifically, we…

Recent advances in text-to-speech technologies have enabled realistic voice generation, fueling audio-based deepfake attacks such as fraud and impersonation. While audio anti-spoofing systems are critical for detecting such threats, prior…

This paper presents an experimental study on deep speaker embedding with an attention mechanism that has been found to be a powerful representation learning technique in speaker recognition. In this framework, an attention model works as a…

Audio DeepFakes are utterances generated with the use of deep neural networks. They are highly misleading and pose a threat due to use in fake news, impersonation, or extortion. In this work, we focus on increasing accessibility to the…

A large number of works view the automatic assessment of speech from an utterance- or system-level perspective. While such approaches are good in judging overall quality, they cannot adequately explain why a certain score was assigned to an…

Deepfake speech utterances can be forged by replacing one or more words in a bona fide utterance with semantically different words synthesized with speech-generative models. While a dedicated synthetic word detector could be developed, we…

Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of…

While promising performance for speaker verification has been achieved by deep speaker embeddings, the advantage would reduce in the case of speaking-style variability. Speaking rate mismatch is often observed in practical speaker…

Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persisting challenge. In this paper, we propose a new self-supervised speaker verification approach, Self-Distillation…

The convolutional neural network (CNN) based approaches have shown great success for speaker verification (SV) tasks, where modeling long temporal context and reducing information loss of speaker characteristics are two important challenges…

Speech tokenization is the task of representing speech signals as a sequence of discrete units. Such representations can be later used for various downstream tasks including automatic speech recognition, text-to-speech, etc. More relevant…

Generalization in audio deepfake detection presents a significant challenge, with models trained on specific datasets often struggling to detect deepfakes generated under varying conditions and unknown algorithms. While collectively…

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…

In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose…

State-of-the-art methods for audio generation suffer from fingerprint artifacts and repeated inconsistencies across temporal and spectral domains. Such artifacts could be well captured by the frequency domain analysis over the spectrogram.…

Traditional speech separation and speaker diarization approaches rely on prior knowledge of target speakers or a predetermined number of participants in audio signals. To address these limitations, recent advances focus on developing…

Representing speech as discrete tokens provides a framework for transforming speech into a format that closely resembles text, thus enabling the use of speech as an input to the widely successful large language models (LLMs). Currently,…

In multi-speaker applications is common to have pre-computed models from enrolled speakers. Using these models to identify the instances in which these speakers intervene in a recording is the task of speaker tracking. In this paper, we…