Related papers: Improving Semi-supervised End-to-end Automatic Spe…
We investigated an enhancement and a domain adaptation approach to make speaker verification systems robust to perturbations of far-field speech. In the enhancement approach, using paired (parallel) reverberant-clean speech, we trained a…
Research on automatic speech recognition (ASR) systems for electrolaryngeal speakers has been relatively unexplored due to small datasets. When training data is lacking in ASR, a large-scale pretraining and fine tuning framework is often…
For the lack of adequate paired noisy-clean speech corpus in many real scenarios, non-parallel training is a promising task for DNN-based speech enhancement methods. However, because of the severe mismatch between input and target speeches,…
Code-Switching (CS) is a common linguistic phenomenon in multilingual communities that consists of switching between languages while speaking. This paper presents our investigations on end-to-end speech recognition for Mandarin-English CS…
This paper focuses on using voice conversion (VC) to improve the speech intelligibility of surgical patients who have had parts of their articulators removed. Due to the difficulty of data collection, VC without parallel data is highly…
Recently image-to-image translation has attracted significant interests in the literature, starting from the successful use of the generative adversarial network (GAN), to the introduction of cyclic constraint, to extensions to multiple…
Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such…
End-to-end automatic speech recognition (ASR) can achieve promising performance with large-scale training data. However, it is known that domain mismatch between training and testing data often leads to a degradation of recognition…
In digital pathology, many image analysis tasks are challenged by the need for large and time-consuming manual data annotations to cope with various sources of variability in the image domain. Unsupervised domain adaptation based on…
This paper presents Fd-CycleGAN, an image-to-image (I2I) translation framework that enhances latent representation learning to approximate real data distributions. Building upon the foundation of CycleGAN, our approach integrates Local…
Emotional Voice Conversion, or emotional VC, is a technique of converting speech from one emotion state into another one, keeping the basic linguistic information and speaker identity. Previous approaches for emotional VC need parallel data…
In the area of multi-domain speech recognition, research in the past focused on hybrid acoustic models to build cross-domain and domain-invariant speech recognition systems. In this paper, we empirically examine the difference in behavior…
Non-parallel voice conversion (VC) is a technique for learning the mapping from source to target speech without relying on parallel data. This is an important task, but it has been challenging due to the disadvantages of the training…
In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian…
In the recent trend of semi-supervised speech recognition, both self-supervised representation learning and pseudo-labeling have shown promising results. In this paper, we propose a novel approach to combine their ideas for end-to-end…
We propose a novel training scheme to optimize voice conversion network with a speaker identity loss function. The training scheme not only minimizes frame-level spectral loss, but also speaker identity loss. We introduce a cycle…
In this paper, a new semi-supervised deep multiple-input multiple-output (MIMO) detection approach using a cycle-consistent generative adversarial network (CycleGAN) is proposed for communication systems without any prior knowledge of…
Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose…
Recently, the cycle-consistent generative adversarial networks (CycleGAN) has been widely used for synthesis of multi-domain medical images. The domain-specific nonlinear deformations captured by CycleGAN make the synthesized images…
Unsupervised image-to-image translation methods such as CycleGAN learn to convert images from one domain to another using unpaired training data sets from different domains. Unfortunately, these approaches still require centrally collected…