Related papers: Recurrent Neural Network Postfilters for Statistic…
Recurrent neural networks (RNNs), particularly long short-term memory (LSTM), have gained much attention in automatic speech recognition (ASR). Although some successful stories have been reported, training RNNs remains highly challenging,…
Employing deep neural networks (DNNs) to directly learn filters for multi-channel speech enhancement has potentially two key advantages over a traditional approach combining a linear spatial filter with an independent tempo-spectral…
Convolutional neural networks (CNNs) with residual links (ResNets) and causal dilated convolutional units have been the network of choice for deep learning approaches to speech enhancement. While residual links improve gradient flow during…
In automatic speech recognition (ASR), model pruning is a widely adopted technique that reduces model size and latency to deploy neural network models on edge devices with resource constraints. However, multiple models with different…
Deep Learning methods employ multiple processing layers to learn hierarchial representations of data. They have already been deployed in a humongous number of applications and have produced state-of-the-art results. Recently with the growth…
Deep Neural Networks (DNN) have been successful in en- hancing noisy speech signals. Enhancement is achieved by learning a nonlinear mapping function from the features of the corrupted speech signal to that of the reference clean speech…
This paper proposes a generative moment matching network (GMMN)-based post-filter that provides inter-utterance pitch variation for deep neural network (DNN)-based singing voice synthesis. The natural pitch variation of a human singing…
The fundamental frequency (F0) contour of speech is a key aspect to represent speech prosody that finds use in speech and spoken language analysis such as voice conversion and speech synthesis as well as speaker and language identification.…
Recurrent neural networks (RNNs) have been successfully applied to various natural language processing (NLP) tasks and achieved better results than conventional methods. However, the lack of understanding of the mechanisms behind their…
This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time. The approach is demonstrated for text (where the data…
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance…
In this paper, we aim at improving the performance of synthesized speech in statistical parametric speech synthesis (SPSS) based on a generative adversarial network (GAN). In particular, we propose a novel architecture combining the…
Deep neural networks (DNNs) are widely used in pattern-recognition tasks for which a human comprehensible, quantitative description of the data-generating process, e.g., in the form of equations, cannot be achieved. While doing so, DNNs…
This paper describes a novel text-to-speech (TTS) technique based on deep convolutional neural networks (CNN), without use of any recurrent units. Recurrent neural networks (RNN) have become a standard technique to model sequential data…
We study the problem of compressing recurrent neural networks (RNNs). In particular, we focus on the compression of RNN acoustic models, which are motivated by the goal of building compact and accurate speech recognition systems which can…
We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task. The algorithm is based on an earlier theoretical result that…
We investigate the problem of incorporating higher-level symbolic score-like information into Automatic Music Transcription (AMT) systems to improve their performance. We use recurrent neural networks (RNNs) and their variants as music…
Substring kernels are classical tools for representing biological sequences or text. However, when large amounts of annotated data are available, models that allow end-to-end training such as neural networks are often preferred. Links…
Recurrent neural networks are convenient and efficient models for language modeling. However, when applied on the level of characters instead of words, they suffer from several problems. In order to successfully model long-term…
In this paper, we have investigated recurrent deep neural networks (DNNs) in combination with regularization techniques as dropout, zoneout, and regularization post-layer. As a benchmark, we chose the TIMIT phone recognition task due to its…