Related papers: FEARLESS STEPS Challenge (FS-2): Supervised Learni…

Few-shot unsupervised domain adaptation (FS-UDA) leverages a limited amount of labeled data from a source domain to enable accurate classification in an unlabeled target domain. Despite recent advancements, current approaches of FS-UDA…

Recent work has explored using self-supervised learning (SSL) speech representations such as wav2vec2.0 as the representation medium in standard two-stage TTS, in place of conventionally used mel-spectrograms. It is however unclear which…

This technical report describes the CP-JKU team's submission for Task 4 Sound Event Detection with Heterogeneous Training Datasets and Potentially Missing Labels of the DCASE 24 Challenge. We fine-tune three large Audio Spectrogram…

Audio deepfake detection is an emerging topic in the artificial intelligence community. The second Audio Deepfake Detection Challenge (ADD 2023) aims to spur researchers around the world to build new innovative technologies that can further…

Face Anti-Spoofing (FAS) is crucial to safeguard Face Recognition (FR) Systems. In real-world scenarios, FRs are confronted with both physical and digital attacks. However, existing algorithms often address only one type of attack at a…

Data collected from the real world typically exhibit long-tailed distributions, where frequent classes contain abundant data while rare ones have only a limited number of samples. While existing supervised learning approaches have been…

We introduce Fish Audio S2, an open-sourced text-to-speech system featuring multi-speaker, multi-turn generation, and, most importantly, instruction-following control via natural-language descriptions. To scale training, we develop a…

Self-supervised learning (SSL) in audio holds significant potential across various domains, particularly in situations where abundant, unlabeled data is readily available at no cost. This is pertinent in bioacoustics, where biologists…

In this report, we describe our submitted system for track 2 of the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22). We fuse a variety of good-performing models ranging from supervised models to self-supervised learning(SSL)…

Designing a speech quality assessment (SQA) system for estimating mean-opinion-score (MOS) of multi-rate speech with varying sampling frequency (16-48 kHz) is a challenging task. The challenge arises due to the limited availability of a…

Modern speech recognition systems exhibits rapid performance degradation under domain shift. This issue is especially prevalent in data-scarce settings, such as low-resource languages, where diversity of training data is limited. In this…

Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…

The ICASSP 2023 Acoustic Echo Cancellation Challenge is intended to stimulate research in acoustic echo cancellation (AEC), which is an important area of speech enhancement and is still a top issue in audio communication. This is the fourth…

The DIarization of SPeaker and LAnguage in Conversational Environments (DISPLACE) 2024 challenge is the second in the series of DISPLACE challenges, which involves tasks of speaker diarization (SD) and language diarization (LD) on a…

Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from…

This paper introduces the ZevoMOS entry to the main track of the VoiceMOS Challenge 2022. The ZevoMOS submission is based on a two-step finetuning of pretrained self-supervised learning (SSL) speech models. The first step uses a task of…

In the era of information explosion, efficiently leveraging large-scale unlabeled data while minimizing the reliance on high-quality pixel-level annotations remains a critical challenge in the field of medical imaging. Semi-supervised…

Existing multi-channel continuous speech separation (CSS) models are heavily dependent on supervised data - either simulated data which causes data mismatch between the training and real-data testing, or the real transcribed overlapping…

The VoicePrivacy Challenge promotes the development of voice anonymisation solutions for speech technology. In this paper we present a systematic overview and analysis of the second edition held in 2022. We describe the voice anonymisation…

To reduce the communication overhead caused by parallel training of multiple clients, various federated learning (FL) techniques use random client sampling. Nonetheless, ensuring the efficacy of random sampling and determining the optimal…