Related papers: Meta-learning with Latent Space Clustering in Gene…

This report presents the system developed by the ABSP Laboratory team for the third DIHARD speech diarization challenge. Our main contribution in this work is to develop a simple and efficient solution for acoustic domain dependent speech…

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…

This paper describes a general, scalable, end-to-end framework that uses the generative adversarial network (GAN) objective to enable robust speech recognition. Encoders trained with the proposed approach enjoy improved invariance by…

Popular neural network-based speech enhancement systems operate on the magnitude spectrogram and ignore the phase mismatch between the noisy and clean speech signals. Conditional generative adversarial networks (cGANs) show promise in…

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…

We propose a new framework to improve automatic speech recognition (ASR) systems in resource-scarce environments using a generative adversarial network (GAN) operating on acoustic input features. The GAN is used to enhance the features of…

The generative adversarial networks (GANs) have facilitated the development of speech enhancement recently. Nevertheless, the performance advantage is still limited when compared with state-of-the-art models. In this paper, we propose a…

Generative adversarial networks (GANs) have succeeded in inducing cross-lingual word embeddings -- maps of matching words across languages -- without supervision. Despite these successes, GANs' performance for the difficult case of distant…

In this paper we propose a new method of speaker diarization that employs a deep learning architecture to learn speaker embeddings. In contrast to the traditional approaches that build their speaker embeddings using manually hand-crafted…

Deep speaker embedding models have been commonly used as a building block for speaker diarization systems; however, the speaker embedding model is usually trained according to a global loss defined on the training data, which could be…

Recent speaker diarisation systems often convert variable length speech segments into fixed-length vector representations for speaker clustering, which are known as speaker embeddings. In this paper, the content-aware speaker embeddings…

The clustering algorithm plays a crucial role in speaker diarization systems. However, traditional clustering algorithms suffer from the complex distribution of speaker embeddings and lack of digging potential relationships between speakers…

Data augmentation is conventionally used to inject robustness in Speaker Verification systems. Several recently organized challenges focus on handling novel acoustic environments. Deep learning based speech enhancement is a modern solution…

In spite of the popularity of end-to-end diarization systems nowadays, modular systems comprised of voice activity detection (VAD), speaker embedding extraction plus clustering, and overlapped speech detection (OSD) plus handling still…

Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers. It is well-known that large-margin training can improve the generalisation…

Speaker diarization systems are challenged by a trade-off between the temporal resolution and the fidelity of the speaker representation. By obtaining a superior temporal resolution with an enhanced accuracy, a multi-scale approach is a way…

Speaker recognition deals with recognizing speakers by their speech. Most speaker recognition systems are built upon two stages, the first stage extracts low dimensional correlation embeddings from speech, and the second performs the…

In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) systems. To alleviate this issue, the commonest way is to use a…

Current speaker recognition technology provides great performance with the x-vector approach. However, performance decreases when the evaluation domain is different from the training domain, an issue usually addressed with domain adaptation…

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding…