Related papers: Wide band sub-band speech coding using nonlinear p…

This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in…

In this paper we present a neural network based estimator system which performs well the frequency extraction from unevenly sampled signals. It uses an unsupervised Hebbian nonlinear neural algorithm to extract the principal components…

Recent advances in neural network -based text-to-speech have reached human level naturalness in synthetic speech. The present sequence-to-sequence models can directly map text to mel-spectrogram acoustic features, which are convenient for…

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

Deep neural network based full-band speech enhancement systems face challenges of high demand of computational resources and imbalanced frequency distribution. In this paper, a light-weight full-band model is proposed with two dedicated…

We experimentally investigated the performance of split nonlinearity compensation schemes for single and multi-channel WDM systems. We show that split NLC SNR gains of more than 0.4 dB at 5540 km can be achieved compared to transmitter- or…

Subband-based approaches process subbands in parallel through the model with shared parameters to learn the commonality of local spectrums for noise reduction. In this way, they have achieved remarkable results with fewer parameters.…

Wideband spectrum sensing (WSS) is an essential technology for cognitive radio. However, the sampling rate is still a bottleneck of WSS. Several sub-Nyquist sensing methods have been proposed. These technologies deteriorate in the low…

Neural speech synthesis models have recently demonstrated the ability to synthesize high quality speech for text-to-speech and compression applications. These new models often require powerful GPUs to achieve real-time operation, so being…

Neural speech synthesis algorithms are a promising new approach for coding speech at very low bitrate. They have so far demonstrated quality that far exceeds traditional vocoders, at the cost of very high complexity. In this work, we…

We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody. We present a generic multi-scale spectrogram prediction mechanism where the system first predicts…

This paper describes a Two-step Band-split Neural Network (TBNN) approach for full-band acoustic echo cancellation. Specifically, after linear filtering, we split the full-band signal into wide-band (16KHz) and high-band (16-48KHz) for…

Signal to Noise Ratio (SNR) is an important index for wireless communications. In CDMA systems, spreading sequences are utilized. This series of papers show the method to derive spreading sequences as the solutions of the non-linear…

In this paper, we propose the FeatherWave, yet another variant of WaveRNN vocoder combining the multi-band signal processing and the linear predictive coding. The LPCNet, a recently proposed neural vocoder which utilized the linear…

Sub-band models have achieved promising results due to their ability to model local patterns in the spectrogram. Some studies further improve the performance by fusing sub-band and full-band information. However, the structure for the…

This paper addresses the problem of multi-channel multi-speech separation based on deep learning techniques. In the short time Fourier transform domain, we propose an end-to-end narrow-band network that directly takes as input the…

We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…

In automatic speech recognition (ASR), wideband (WB) and narrowband (NB) speech signals with different sampling rates typically use separate acoustic models. Therefore mixed-bandwidth (MB) acoustic modeling has important practical values…

We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combine models which operate at different granularities (e.g.…

We explore pretraining strategies including choice of base corpus with the aim of choosing the best strategy for zero-shot multi-speaker end-to-end synthesis. We also examine choice of neural vocoder for waveform synthesis, as well as…