Related papers: Data Augmentation for Diverse Voice Conversion in …
Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with small annotated datasets. Despite this, speech SSL representations may fail while…
Data Augmentation (DA) is frequently used to provide additional training data without extra human annotation automatically. However, data augmentation may introduce noisy data that impairs training. To guarantee the quality of augmented…
Text-to-Speech (TTS) systems in Lombard speaking style can improve the overall intelligibility of speech, useful for hearing loss and noisy conditions. However, training those models requires a large amount of data and the Lombard effect is…
Although speech recognition algorithms have developed quickly in recent years, achieving high transcription accuracy across diverse audio formats and acoustic environments remains a major challenge. This work explores how incorporating…
Recent success of the Tacotron speech synthesis architecture and its variants in producing natural sounding multi-speaker synthesized speech has raised the exciting possibility of replacing expensive, manually transcribed, domain-specific,…
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…
Recent advances with self-supervised learning have allowed speech recognition systems to achieve state-of-the-art (SOTA) word error rates (WER) while requiring only a fraction of the labeled training data needed by its predecessors.…
Voice Conversion(VC) refers to changing the timbre of a speech while retaining the discourse content. Recently, many works have focused on disentangle-based learning techniques to separate the timbre and the linguistic content information…
The task of making speaker verification systems robust to adverse scenarios remain a challenging and an active area of research. We developed an unsupervised feature enhancement approach in log-filter bank domain with the end goal of…
Deep learning based singing voice synthesis (SVS) systems have been demonstrated to flexibly generate singing with better qualities, compared to conventional statistical parametric based methods. However, neural systems are generally…
Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many AC approaches rely on source-target parallel speech data. We propose a…
In this study, we address the challenge of speaker recognition using a novel data augmentation technique of adding noise to enrollment files. This technique efficiently aligns the sources of test and enrollment files, enhancing…
Self-supervision has shown great potential for audio-visual speech recognition by vastly reducing the amount of labeled data required to build good systems. However, existing methods are either not entirely end-to-end or do not train joint…
We propose a flexible framework that deals with both singer conversion and singers vocal technique conversion. The proposed model is trained on non-parallel corpora, accommodates many-to-many conversion, and leverages recent advances of…
Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative…
Zero-shot voice conversion aims to transfer the voice of a source speaker to that of a speaker unseen during training, while preserving the content information. Although various methods have been proposed to reconstruct speaker information…
This paper presents an analysis of speech synthesis quality achieved by simultaneously performing voice conversion and language code-switching using multilingual VQ-VAE speech synthesis in German, French, English and Italian. In this paper,…
In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks. However, the fine-tuning strategies for adapting those pre-trained models to speaker verification…
This paper introduces a novel application of Test-Time Training (TTT) for Speech Enhancement, addressing the challenges posed by unpredictable noise conditions and domain shifts. This method combines a main speech enhancement task with a…
Large Language Models (LLMs) are one of the most promising technologies for the next era of speech generation systems, due to their scalability and in-context learning capabilities. Nevertheless, they suffer from multiple stability issues…