Related papers: WaveNet: A Generative Model for Raw Audio

While traditional statistical signal processing model-based methods can derive the optimal estimators relying on specific statistical assumptions, current learning-based methods further promote the performance upper bound via deep neural…

Directly learning to generate audio waveforms in an autoregressive manner is a challenging task, due to the length of the raw sequences and the existence of important structure on many different timescales. Traditional approaches based on…

Current fake audio detection relies on hand-crafted features, which lose information during extraction. To overcome this, recent studies use direct feature extraction from raw audio signals. For example, RawNet is one of the representative…

In this paper, we propose a technique to alleviate the quality degradation caused by collapsed speech segments sometimes generated by the WaveNet vocoder. The effectiveness of the WaveNet vocoder for generating natural speech from acoustic…

Classical parametric speech coding techniques provide a compact representation for speech signals. This affords a very low transmission rate but with a reduced perceptual quality of the reconstructed signals. Recently, autoregressive deep…

In this work, we present CleanUNet, a causal speech denoising model on the raw waveform. The proposed model is based on an encoder-decoder architecture combined with several self-attention blocks to refine its bottleneck representations,…

Recent neural waveform synthesizers such as WaveNet, WaveGlow, and the neural-source-filter (NSF) model have shown good performance in speech synthesis despite their different methods of waveform generation. The similarity between speech…

The recent developments in technology have re-warded us with amazing audio synthesis models like TACOTRON and WAVENETS. On the other side, it poses greater threats such as speech clones and deep fakes, that may go undetected. To tackle…

We describe speaker-independent speech synthesis driven by a small set of phonetically meaningful speech parameters such as formant frequencies. The intention is to leverage deep-learning advances to provide a highly realistic signal…

We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly. Given input audio containing speech corrupted by an additive background signal, the system aims to produce a processed…

We propose a new deep network for audio event recognition, called AENet. In contrast to speech, sounds coming from audio events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an…

In this work, we extend ClariNet (Ping et al., 2019), a fully end-to-end speech synthesis model (i.e., text-to-wave), to generate high-fidelity speech from multiple speakers. To model the unique characteristic of different voices, low…

Unsupervised deep learning has recently demonstrated the promise of producing high-quality samples. While it has tremendous potential to promote the image colorization task, the performance is limited owing to the high-dimension of data…

Efficient audio synthesis is an inherently difficult machine learning task, as human perception is sensitive to both global structure and fine-scale waveform coherence. Autoregressive models, such as WaveNet, model local structure at the…

In this paper we propose WaveGlow: a flow-based network capable of generating high quality speech from mel-spectrograms. WaveGlow combines insights from Glow and WaveNet in order to provide fast, efficient and high-quality audio synthesis,…

Closed-Set speaker identification aims to assign a speech utterance to one of a predefined set of enrolled speakers and requires robust modeling of speaker-specific characteristics across multiple temporal scales. While recent deep learning…

In this work, we propose a multi-head relevance weighting framework to learn audio representations from raw waveforms. The audio waveform, split into windows of short duration, are processed with a 1-D convolutional layer of cosine…

We present a deep convolutional GAN which leverages techniques from MP3/Vorbis audio compression to produce long, high-quality audio samples with long-range coherence. The model uses a Modified Discrete Cosine Transform (MDCT) data…

Despite achieving satisfactory performance in speaker verification using deep neural networks, variable-duration utterances remain a challenge that threatens the robustness of systems. To deal with this issue, we propose a speaker…

In this paper we present a domain adaptation technique for formant estimation using a deep network. We first train a deep learning network on a small read speech dataset. We then freeze the parameters of the trained network and use several…