Related papers: Universal Robust Speech Adaptation for Cross-Domai…

This paper introduces OmniGSE, a novel general speech enhancement (GSE) framework designed to mitigate the diverse distortions that speech signals encounter in real-world scenarios. These distortions include background noise, reverberation,…

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,…

Adversarial training of end-to-end (E2E) ASR systems using generative adversarial networks (GAN) has recently been explored for low-resource ASR corpora. GANs help to learn the true data representation through a two-player min-max game.…

This paper proposes a simple yet effective way of regularising the encoder-decoder-based automatic speech recognition (ASR) models that enhance the robustness of the model and improve the generalisation to out-of-domain scenarios. The…

Nowadays vast amounts of speech data are recorded from low-quality recorder devices such as smartphones, tablets, laptops, and medium-quality microphones. The objective of this research was to study the automatic generation of high-quality…

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…

Generative adversarial networks have led to significant advances in cross-modal/domain translation. However, typically these networks are designed for a specific task (e.g., dialogue generation or image synthesis, but not both). We present…

The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning models. Therefore, we propose an intra-source style…

Despite huge improvements in automatic speech recognition (ASR) employing neural networks, ASR systems still suffer from a lack of robustness and generalizability issues due to domain shifting. This is mainly because principal corpus design…

Face anti-spoofing (FAS) approaches based on unsupervised domain adaption (UDA) have drawn growing attention due to promising performances for target scenarios. Most existing UDA FAS methods typically fit the trained models to the target…

An utterance-level speaker embedding is typically obtained by aggregating a sequence of frame-level representations. However, in real-world scenarios, individual frames encode not only speaker-relevant information but also various nuisance…

Speech enhancement (SE) is proved effective in reducing noise from noisy speech signals for downstream automatic speech recognition (ASR), where multi-task learning strategy is employed to jointly optimize these two tasks. However, the…

We investigate and characterize the inherent resilience of conditional Generative Adversarial Networks (cGANs) against noise in their conditioning labels, and exploit this fact in the context of Unsupervised Domain Adaptation (UDA). In UDA,…

Automatic Speech Recognition (ASR) systems must be robust to the myriad types of noises present in real-world environments including environmental noise, room impulse response, special effects as well as attacks by malicious actors…

The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…

Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (NLP) modules. The errors of the ASR system can seriously…

Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources. We propose a novel generative model based on cyclic-consistent generative adversarial network (CycleGAN) for…

Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage language models…

Most GAN(Generative Adversarial Network)-based approaches towards high-fidelity waveform generation heavily rely on discriminators to improve their performance. However, GAN methods introduce much uncertainty into the generation process and…

We propose AudioStyleGAN (ASGAN), a new generative adversarial network (GAN) for unconditional speech synthesis. As in the StyleGAN family of image synthesis models, ASGAN maps sampled noise to a disentangled latent vector which is then…