Related papers: FINALLY: fast and universal speech enhancement wit…

Speech enhancement deep learning systems usually require large amounts of training data to operate in broad conditions or real applications. This makes the adaptability of those systems into new, low resource environments an important…

Generative Universal Speech Enhancement (USE) methods aim to leverage generative models to improve speech quality under various types of distortions. However, existing generative speech enhancement methods often suffer from semantic…

We propose Parallel WaveGAN, a distillation-free, fast, and small-footprint waveform generation method using a generative adversarial network. In the proposed method, a non-autoregressive WaveNet is trained by jointly optimizing…

Machine recognition of an atypical speech like whispered speech, is a challenging task. We introduce whisper-to-natural-speech conversion using sequence-to-sequence approach by proposing enhanced transformer architecture, which uses both…

The classification of acoustic environments allows for machines to better understand the auditory world around them. The use of deep learning in order to teach machines to discriminate between different rooms is a new area of research.…

Speech enhancement at extremely low signal-to-noise ratio (SNR) condition is a very challenging problem and rarely investigated in previous works. This paper proposes a robust speech enhancement approach (UNetGAN) based on U-Net and…

Artificial speech synthesis has made a great leap in terms of naturalness as recent Text-to-Speech (TTS) systems are capable of producing speech with similar quality to human recordings. However, not all speaking styles are easy to model:…

Logical Access (LA) attacks, also known as audio deepfake attacks, use Text-to-Speech (TTS) or Voice Conversion (VC) methods to generate spoofed speech data. This can represent a serious threat to Automatic Speaker Verification (ASV)…

Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of…

Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech…

We propose Relativistic Adversarial Feedback (RAF), a novel training objective for GAN vocoders that improves in-domain fidelity and generalization to unseen scenarios. Although modern GAN vocoders employ advanced architectures, their…

Feature-mapping with deep neural networks is commonly used for single-channel speech enhancement, in which a feature-mapping network directly transforms the noisy features to the corresponding enhanced ones and is trained to minimize the…

Recently, GAN based speech synthesis methods, such as MelGAN, have become very popular. Compared to conventional autoregressive based methods, parallel structures based generators make waveform generation process fast and stable. However,…

Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in face of various practical environments. However, such…

Lately, the self-attention mechanism has marked a new milestone in the field of automatic speech recognition (ASR). Nevertheless, its performance is susceptible to environmental intrusions as the system predicts the next output symbol…

Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…

Audio captioning aims at generating natural language descriptions for audio clips automatically. Existing audio captioning models have shown promising improvement in recent years. However, these models are mostly trained via maximum…

While deep learning based speech enhancement systems have made rapid progress in improving the quality of speech signals, they can still produce outputs that contain artifacts and can sound unnatural. We propose a novel approach to speech…

The existing fake audio detection systems often rely on expert experience to design the acoustic features or manually design the hyperparameters of the network structure. However, artificial adjustment of the parameters can have a…

This paper presents an adversarial learning method for recognition-synthesis based non-parallel voice conversion. A recognizer is used to transform acoustic features into linguistic representations while a synthesizer recovers output…