Related papers: Voice2Series: Reprogramming Acoustic Models for Ti…
Diffusion-based text-to-speech (TTS) systems have made remarkable progress in zero-shot speech synthesis, yet optimizing all components for perceptual metrics remains challenging. Prior work with DMOSpeech demonstrated direct metric…
This paper presents a new voice impersonation attack using voice conversion (VC). Enrolling personal voices for automatic speaker verification (ASV) offers natural and flexible biometric authentication systems. Basically, the ASV systems do…
This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on nearly half a million hours of publicly available speech audio in 128…
Piano audio-to-score transcription (A2S) is an important yet underexplored task with extensive applications for music composition, practice, and analysis. However, existing end-to-end piano A2S systems faced difficulties in retrieving…
We propose an approach for training speaker identification models in a weakly supervised manner. We concentrate on the setting where the training data consists of a set of audio recordings and the speaker annotation is provided only at the…
Feature representations derived from models pre-trained on large-scale datasets have shown their generalizability on a variety of audio analysis tasks. Despite this generalizability, however, task-specific features can outperform if…
Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. Nonetheless, without sufficient data, seq2seq VC models can suffer from unstable training and mispronunciation problems in…
Modern speaker recognition system relies on abundant and balanced datasets for classification training. However, diverse defective datasets, such as partially-labelled, small-scale, and imbalanced datasets, are common in real-world…
Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…
In recent years, self-supervised learning has excelled for its capacity to learn robust feature representations from unlabelled data. Networks pretrained through self-supervision serve as effective feature extractors for downstream tasks,…
The monotonic ordinal classification has increased the interest of researchers and practitioners within machine learning community in the last years. In real applications, the problems with monotonicity constraints are very frequent. To…
Time series data are inherently functions of time, yet current transformers often learn time series by modeling them as mere concatenations of time periods, overlooking their functional properties. In this work, we propose a novel objective…
Advances in machine learning have made it possible to perform various text and speech processing tasks, such as automatic speech recognition (ASR), in an end-to-end (E2E) manner. E2E approaches utilizing pre-trained models are gaining…
Modern phonetic research regularly makes use of automatic tools for the annotation of speech data, however few tools exist for the annotation of many variable phonetic phenomena. At the same time, pre-trained self-supervised models, such as…
We propose an automatic data processing pipeline to extract vocal productions from large-scale natural audio recordings and classify these vocal productions. The pipeline is based on a deep neural network and adresses both issues…
Visual Speech Recognition (VSR) differs from the common perception tasks as it requires deeper reasoning over the video sequence, even by human experts. Despite the recent advances in VSR, current approaches rely on labeled data to fully…
Classification of time series is a growing problem in different disciplines due to the progressive digitalization of the world. Currently, the state-of-the-art in time series classification is dominated by The Hierarchical Vote Collective…
Time series shapelets are discriminative sub-sequences and their similarity to time series can be used for time series classification. Initial shapelet extraction algorithms searched shapelets by complete enumeration of all possible data…
Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the…
A key function of auditory cognition is the association of characteristic sounds with their corresponding semantics over time. Humans attempting to discriminate between fine-grained audio categories, often replay the same discriminative…