We describe a new convolutional framework for waveform evaluation, WEnets, and build a Narrowband Audio Waveform Evaluation Network, or NAWEnet, using this framework. NAWEnet is single-ended (or no-reference) and was trained three separate times in order to emulate PESQ, POLQA, or STOI with testing correlations 0.95, 0.92, and 0.95, respectively when training on only 50% of available data and testing on 40%. Stacks of 1-D convolutional layers and non-linear downsampling learn which features are important for quality or intelligibility estimation. This straightforward architecture simplifies the interpretation of its inner workings and paves the way for future investigations into higher sample rates and accurate no-reference subjective speech quality predictions.
This study investigated the waveform representation for audio signal classification. Recently, many studies on audio waveform classification such as acoustic event detection and music genre classification have been published. Most studies on audio waveform classification have proposed the use of a deep learning (neural network) framework. Generally, a frequency analysis method such as Fourier transform is applied to extract the frequency or spectral information from the input audio waveform before inputting the raw audio waveform into the neural network. In contrast to these previous studies, …
Convolutional neural networks contain strong priors for generating natural looking images [1]. These priors enable image denoising, super resolution, and inpainting in an unsupervised manner. Previous attempts to demonstrate similar ideas in audio, namely deep audio priors, (i) use hand picked architectures such as harmonic convolutions, (ii) only work with spectrogram input, and (iii) have been used mostly for eliminating Gaussian noise [2]. In this work we show that existing SOTA architectures for audio source separation contain deep priors even when working with the raw waveform. Deep prior…
National Technical University of Athens（雅典国立技术大学）；Athena Research Center（雅典娜研究中心）
Sound Event Detection and Audio Classification tasks are traditionally addressed through time-frequency representations of audio signals such as spectrograms. However, the emergence of deep neural networks as efficient feature extractors has enabled the direct use of audio signals for classification purposes. In this paper, we attempt to recognize musical instruments in polyphonic audio by only feeding their raw waveforms into deep learning models. Various recurrent and convolutional architectures incorporating residual connections are examined and parameterized in order to build end-to-end cl…
Technion – Israel Institute of Technology（以色列理工学院）
Models for audio generation are typically trained on hours of recordings. Here, we illustrate that capturing the essence of an audio source is typically possible from as little as a few tens of seconds from a single training signal. Specifically, we present a GAN-based generative model that can be trained on one short audio signal from any domain (e.g. speech, music, etc.) and does not require pre-training or any other form of external supervision. Once trained, our model can generate random samples of arbitrary duration that maintain semantic similarity to the training waveform, yet exhibit n…
Zhejiang University（浙江大学）；State Key Laboratory of Media Convergence Production Technology and Systems（媒体融合生产技术与系统国家重点实验室）
Audio super-resolution is the task of constructing a high-resolution (HR) audio from a low-resolution (LR) audio by adding the missing band. Previous methods based on convolutional neural networks and mean squared error training objective have relatively low performance, while adversarial generative models are difficult to train and tune. Recently, normalizing flow has attracted a lot of attention for its high performance, simple training and fast inference. In this paper, we propose WSRGlow, a Glow-based waveform generative model to perform audio super-resolution. Specifically, 1) we integrat…
In [1,2] authors provided preliminary results for synthesizing speech from electroencephalography (EEG) features where they first predict acoustic features from EEG features and then the speech is reconstructed from the predicted acoustic features using griffin lim reconstruction algorithm. In this paper we first introduce a deep learning model that takes raw EEG waveform signals as input and directly produces audio waveform as output. We then demonstrate predicting 16 different acoustic features from EEG features. We demonstrate our results for both spoken and listen condition in this paper. …
McGill University（麦吉尔大学）；École de Technologie Superiéure, Université du Québec（魁北克大学高等技术学院）；Pontifical Catholic University of Paraná（巴拉那天主教大学）
This paper shows the susceptibility of spectrogram-based audio classifiers to adversarial attacks and the transferability of such attacks to audio waveforms. Some commonly used adversarial attacks to images have been applied to Mel-frequency and short-time Fourier transform spectrograms, and such perturbed spectrograms are able to fool a 2D convolutional neural network (CNN). Such attacks produce perturbed spectrograms that are visually imperceptible by humans. Furthermore, the audio waveforms reconstructed from the perturbed spectrograms are also able to fool a 1D CNN trained on the original …
Music, speech, and acoustic scene sound are often handled separately in the audio domain because of their different signal characteristics. However, as the image domain grows rapidly by versatile image classification models, it is necessary to study extensible classification models in the audio domain as well. In this study, we approach this problem using two types of sample-level deep convolutional neural networks that take raw waveforms as input and uses filters with small granularity. One is a basic model that consists of convolution and pooling layers. The other is an improved model that a…
Duke University（杜克大学）；Duke Kunshan University（昆山杜克大学）
The present paper proposes a waveform boundary detection system for audio spoofing attacks containing partially manipulated segments. Partially spoofed/fake audio, where part of the utterance is replaced, either with synthetic or natural audio clips, has recently been reported as one scenario of audio deepfakes. As deepfakes can be a threat to social security, the detection of such spoofing audio is essential. Accordingly, we propose to address the problem with a deep learning-based frame-level detection system that can detect partially spoofed audio and locate the manipulated pieces. Our prop…
Kyungpook National University（庆北国立大学）；Electronics and Telecommunications Research Institute（韩国电子通信研究院）
Deep generative models for audio synthesis have recently been significantly improved. However, the task of modeling raw-waveforms remains a difficult problem, especially for audio waveforms and music signals. Recently, the realtime audio variational autoencoder (RAVE) method was developed for high-quality audio waveform synthesis. The RAVE method is based on the variational autoencoder and utilizes the two-stage training strategy. Unfortunately, the RAVE model is limited in reproducing wide-pitch polyphonic music sound. Therefore, to enhance the reconstruction performance, we adopt the pitch a…
Differentiable Wavetable Synthesis (DWTS) is a technique for neural audio synthesis which learns a dictionary of one-period waveforms i.e. wavetables, through end-to-end training. We achieve high-fidelity audio synthesis with as little as 10 to 20 wavetables and demonstrate how a data-driven dictionary of waveforms opens up unprecedented one-shot learning paradigms on short audio clips. Notably, we show audio manipulations, such as high quality pitch-shifting, using only a few seconds of input audio. Lastly, we investigate performance gains from using learned wavetables for realtime and intera…
Audio classification can distinguish different kinds of sounds, which is helpful for intelligent applications in daily life. However, it remains a challenging task since the sound events in an audio clip is probably multiple, even overlapping. This paper introduces an end-to-end audio classification system based on raw waveforms and mix-training strategy. Compared to human-designed features which have been widely used in existing research, raw waveforms contain more complete information and are more appropriate for multi-label classification. Taking raw waveforms as input, our network consists…
This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density. The model is built on prior work on score matching and diffusion probabilistic models. It starts from a Gaussian white noise signal and iteratively refines the signal via a gradient-based sampler conditioned on the mel-spectrogram. WaveGrad offers a natural way to trade inference speed for sample quality by adjusting the number of refinement steps, and bridges the gap between non-autoregressive and autoregressive models in terms of audio quality. We find that it can genera…
Developing architectures suitable for modeling raw audio is a challenging problem due to the high sampling rates of audio waveforms. Standard sequence modeling approaches like RNNs and CNNs have previously been tailored to fit the demands of audio, but the resultant architectures make undesirable computational tradeoffs and struggle to model waveforms effectively. We propose SaShiMi, a new multi-scale architecture for waveform modeling built around the recently introduced S4 model for long sequence modeling. We identify that S4 can be unstable during autoregressive generation, and provide a si…
IRCAM - Sorbonne Université（IRCAM - 索邦大学）；CNRS UMR 9912（法国国家科学研究中心 UMR 9912）
Deep generative models applied to audio have improved by a large margin the state-of-the-art in many speech and music related tasks. However, as raw waveform modelling remains an inherently difficult task, audio generative models are either computationally intensive, rely on low sampling rates, are complicated to control or restrict the nature of possible signals. Among those models, Variational AutoEncoders (VAE) give control over the generation by exposing latent variables, although they usually suffer from low synthesis quality. In this paper, we introduce a Realtime Audio Variational autoE…
In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation. The model is non-autoregressive, and converts the white noise signal into structured waveform through a Markov chain with a constant number of steps at synthesis. It is efficiently trained by optimizing a variant of variational bound on the data likelihood. DiffWave produces high-fidelity audios in different waveform generation tasks, including neural vocoding conditioned on mel spectrogram, class-conditional generation, and unconditional generation. We demonstrat…
Indian Institute of Science（印度科学理工学院）；Microsoft India Development Center（微软印度研发中心）
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 modulated Gaussian filters acting as a learnable filterbank. The key novelty of the proposed framework is the introduction of multi-head relevance on the learnt filterbank representations. Each head of the relevance network is modelled as a separate sub-network. These heads perform representation enhancement by generating weight masks for different parts of the time…
We consider source coding of audio signals with the help of a generative model. We use a construction where a waveform is first quantized, yielding a finite bitrate representation. The waveform is then reconstructed by random sampling from a model conditioned on the quantized waveform. The proposed coding scheme is theoretically analyzed. Using SampleRNN as the generative model, we demonstrate that the proposed coding structure provides performance competitive with state-of-the-art source coding tools for specific categories of audio signals.
Transformers have seen an unprecedented rise in Natural Language Processing and Computer Vision tasks. However, in audio tasks, they are either infeasible to train due to extremely large sequence length of audio waveforms or incur a performance penalty when trained on Fourier-based features. In this work, we introduce an architecture, Audiomer, where we combine 1D Residual Networks with Performer Attention to achieve state-of-the-art performance in keyword spotting with raw audio waveforms, outperforming all previous methods while being computationally cheaper and parameter-efficient. Addition…
We learn audio representations by solving a novel self-supervised learning task, which consists of predicting the phase of the short-time Fourier transform from its magnitude. A convolutional encoder is used to map the magnitude spectrum of the input waveform to a lower dimensional embedding. A convolutional decoder is then used to predict the instantaneous frequency (i.e., the temporal rate of change of the phase) from such embedding. To evaluate the quality of the learned representations, we evaluate how they transfer to a wide variety of downstream audio tasks. Our experiments reveal that t…
National Institute of Informatics（国立信息学研究所）；SOKENDAI（综合研究大学院大学）；University of Science and Technology of China（中国科学技术大学）
High-quality speech corpora are essential foundations for most speech applications. However, such speech data are expensive and limited since they are collected in professional recording environments. In this work, we propose an encoder-decoder neural network to automatically enhance low-quality recordings to professional high-quality recordings. To address channel variability, we first filter out the channel characteristics from the original input audio using the encoder network with adversarial training. Next, we disentangle the channel factor from a reference audio. Conditioned on this fact…
This paper proposes a novel way of doing audio synthesis at the waveform level using Transformer architectures. We propose a deep neural network for generating waveforms, similar to wavenet. This is fully probabilistic, auto-regressive, and causal, i.e. each sample generated depends only on the previously observed samples. Our approach outperforms a widely used wavenet architecture by up to 9% on a similar dataset for predicting the next step. Using the attention mechanism, we enable the architecture to learn which audio samples are important for the prediction of the future sample. We show ho…
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 expense of global latent structure and slow iterative sampling, while Generative Adversarial Networks (GANs), have global latent conditioning and efficient parallel sampling, but struggle to generate locally-coherent audio waveforms. Herein, we demonstrate that GANs can in fact generate high-fidelity and locally-coherent audio by modeling log magnitudes and in…
APCodec: A Neural Audio Codec with Parallel Amplitude and Phase Spectrum Encoding and Decoding
University of Science and Technology of China（中国科学技术大学）；National Engineering Research Center of Speech and Language Information Processing（国家语言语音信息处理工程研究中心）
The Chinese University of Hong Kong（香港中文大学）；Sogou Inc.（搜狗公司）；Tencent PCG AIBU（腾讯平台与内容事业群AI业务单元）
Adversarial waveform generation has been a popular approach as the backend of singing voice conversion (SVC) to generate high-quality singing audio. However, the instability of GAN also leads to other problems, such as pitch jitters and U/V errors. It affects the smoothness and continuity of harmonics, hence degrades the conversion quality seriously. This paper proposes to feed harmonic signals to the SVC model in advance to enhance audio generation. We extract the sine excitation from the pitch, and filter it with a linear time-varying (LTV) filter estimated by a neural network. Both these tw…
This paper introduces R-MelNet, a two-part autoregressive architecture with a frontend based on the first tier of MelNet and a backend WaveRNN-style audio decoder for neural text-to-speech synthesis. Taking as input a mixed sequence of characters and phonemes, with an optional audio priming sequence, this model produces low-resolution mel-spectral features which are interpolated and used by a WaveRNN decoder to produce an audio waveform. Coupled with half precision training, R-MelNet uses under 11 gigabytes of GPU memory on a single commodity GPU (NVIDIA 2080Ti). We detail a number of critical…
Imperial College London（伦敦帝国理工学院）；Samsung AI Centre Cambridge（三星剑桥人工智能中心）；University of Augsburg（奥格斯堡大学）；Facebook London（脸书伦敦）
Video-to-speech is the process of reconstructing the audio speech from a video of a spoken utterance. Previous approaches to this task have relied on a two-step process where an intermediate representation is inferred from the video, and is then decoded into waveform audio using a vocoder or a waveform reconstruction algorithm. In this work, we propose a new end-to-end video-to-speech model based on Generative Adversarial Networks (GANs) which translates spoken video to waveform end-to-end without using any intermediate representation or separate waveform synthesis algorithm. Our model consist…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；Adobe Research（奥多比研究院）
Consumer-grade music recordings such as those captured by mobile devices typically contain distortions in the form of background noise, reverb, and microphone-induced EQ. This paper presents a deep learning approach to enhance low-quality music recordings by combining (i) an image-to-image translation model for manipulating audio in its mel-spectrogram representation and (ii) a music vocoding model for mapping synthetically generated mel-spectrograms to perceptually realistic waveforms. We find that this approach to music enhancement outperforms baselines which use classical methods for mel-sp…
National Institute of Informatics, Tokyo, Japan（日本东京国立信息学研究所）；Department of Signal Processing and Acoustics, Aalto University, Finland（芬兰阿尔托大学信号处理与声学系）
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 and music audio synthesis techniques suggests interesting avenues to explore in terms of the best way to apply speech synthesizers in the music domain. This work compares three neural synthesizers used for musical instrument sounds generation under three scenarios: training from scratch on music data, zero-shot learning from the speech domain, and fine-tuning-…
This paper introduces WaveGrad 2, a non-autoregressive generative model for text-to-speech synthesis. WaveGrad 2 is trained to estimate the gradient of the log conditional density of the waveform given a phoneme sequence. The model takes an input phoneme sequence, and through an iterative refinement process, generates an audio waveform. This contrasts to the original WaveGrad vocoder which conditions on mel-spectrogram features, generated by a separate model. The iterative refinement process starts from Gaussian noise, and through a series of refinement steps (e.g., 50 steps), progressively re…
Singapore University of Technology and Design（新加坡科技设计大学）；Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究院）；Yong Siew Toh Conservatory of Music, National University of Singapore（新加坡国立大学杨秀桃音乐学院）
Converting time domain waveforms to frequency domain spectrograms is typically considered to be a prepossessing step done before model training. This approach, however, has several drawbacks. First, it takes a lot of hard disk space to store different frequency domain representations. This is especially true during the model development and tuning process, when exploring various types of spectrograms for optimal performance. Second, if another dataset is used, one must process all the audio clips again before the network can be retrained. In this paper, we integrate the time domain to frequenc…
Most GAN(Generative Adversarial Network)-based approaches towards high-fidelity waveform generation heavily rely on discriminators to improve their performance. However, GAN methods introduce much uncertainty into the generation process and often result in mismatches of pitch and intensity, which is fatal when it comes to sensitive use cases such as singing voice synthesis(SVS). To address this problem, we propose RefineGAN, a high-fidelity neural vocoder focused on the robustness, pitch and intensity accuracy, and high-speed full-band audio generation. We applyed a pitch-guided refine archite…
In this paper, we propose WG-WaveNet, a fast, lightweight, and high-quality waveform generation model. WG-WaveNet is composed of a compact flow-based model and a post-filter. The two components are jointly trained by maximizing the likelihood of the training data and optimizing loss functions on the frequency domains. As we design a flow-based model that is heavily compressed, the proposed model requires much less computational resources compared to other waveform generation models during both training and inference time; even though the model is highly compressed, the post-filter maintains th…
Graduate School of Informatics, Nagoya University（名古屋大学情报学研究科）；Graduate School of Information Science, Nagoya University（名古屋大学情报科学研究科）；Information Technology Center, Nagoya University（名古屋大学信息技术中心）
In this paper, a pitch-adaptive waveform generative model named Quasi-Periodic WaveNet (QPNet) is proposed to improve the limited pitch controllability of vanilla WaveNet (WN) using pitch-dependent dilated convolution neural networks (PDCNNs). Specifically, as a probabilistic autoregressive generation model with stacked dilated convolution layers, WN achieves high-fidelity audio waveform generation. However, the pure-data-driven nature and the lack of prior knowledge of audio signals degrade the pitch controllability of WN. For instance, it is difficult for WN to precisely generate the periodi…
Department of Brain and Cognitive Sciences, MIT, USA（脑科学与认知科学系，麻省理工学院）；McGovern Institute for Brain Research, MIT, USA（脑研究麦戈文研究所，麻省理工学院）；Center for Brains, Minds and Machines, MIT, USA（脑、心智与机器中心，麻省理工学院）；MIT-IBM Watson AI Lab, IBM Research, USA（麻省理工-IBM沃森人工智能实验室，IBM研究院）
STFTCodec: High-Fidelity Audio Compression through Time-Frequency Domain Representation
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；International Digital Economy Academy (IDEA)（国际数字经济学院（IDEA））；Shenzhen Graduate School, Peking University（北京大学深圳研究生院）
Facebook AI Research（脸书人工智能研究院）；INRIA（法国国家信息与自动化研究所）；ENS（巴黎高等师范学院）；PSL Research University（巴黎文理研究大学）；LSCP（语言认知与计算实验室）；EHESS（法国高等社会科学研究院）；CNRS（法国国家科学研究中心）；École Normale Supérieure（巴黎高等师范学院）
Recent progress in deep learning for audio synthesis opens the way to models that directly produce the waveform, shifting away from the traditional paradigm of relying on vocoders or MIDI synthesizers for speech or music generation. Despite their successes, current state-of-the-art neural audio synthesizers such as WaveNet and SampleRNN suffer from prohibitive training and inference times because they are based on autoregressive models that generate audio samples one at a time at a rate of 16kHz. In this work, we study the more computationally efficient alternative of generating the waveform f…
Universitat Pompeu Fabra（庞培法布拉大学）；Pandora Media Inc.（潘多拉媒体公司）
The lack of data tends to limit the outcomes of deep learning research, particularly when dealing with end-to-end learning stacks processing raw data such as waveforms. In this study, 1.2M tracks annotated with musical labels are available to train our end-to-end models. This large amount of data allows us to unrestrictedly explore two different design paradigms for music auto-tagging: assumption-free models - using waveforms as input with very small convolutional filters; and models that rely on domain knowledge - log-mel spectrograms with a convolutional neural network designed to learn timb…
Baidu Silicon Valley Artificial Intelligence Lab（百度硅谷人工智能实验室）
We propose the multi-head convolutional neural network (MCNN) architecture for waveform synthesis from spectrograms. Nonlinear interpolation in MCNN is employed with transposed convolution layers in parallel heads. MCNN achieves more than an order of magnitude higher compute intensity than commonly-used iterative algorithms like Griffin-Lim, yielding efficient utilization for modern multi-core processors, and very fast (more than 300x real-time) waveform synthesis. For training of MCNN, we use a large-scale speech recognition dataset and losses defined on waveforms that are related to perceptu…
Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School（戈登医学成像中心，麻省总医院与哈佛医学院）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland School of Dentistry（马里兰大学牙科学院）
Investigating the relationship between internal tissue point motion of the tongue and oropharyngeal muscle deformation measured from tagged MRI and intelligible speech can aid in advancing speech motor control theories and developing novel treatment methods for speech related-disorders. However, elucidating the relationship between these two sources of information is challenging, due in part to the disparity in data structure between spatiotemporal motion fields (i.e., 4D motion fields) and one-dimensional audio waveforms. In this work, we present an efficient encoder-decoder translation netwo…
Deep learning has dramatically improved the performance of sounds recognition. However, learning acoustic models directly from the raw waveform is still challenging. Current waveform-based models generally use time-domain convolutional layers to extract features. The features extracted by single size filters are insufficient for building discriminative representation of audios. In this paper, we propose multi-scale convolution operation, which can get better audio representation by improving the frequency resolution and learning filters cross all frequency area. For leveraging the waveform-bas…
Korea University（高丽大学）；Netmarble Corporation（网石公司）
Although recent works on neural vocoder have improved the quality of synthesized audio, there still exists a gap between generated and ground-truth audio in frequency space. This difference leads to spectral artifacts such as hissing noise or reverberation, and thus degrades the sample quality. In this paper, we propose Fre-GAN which achieves frequency-consistent audio synthesis with highly improved generation quality. Specifically, we first present resolution-connected generator and resolution-wise discriminators, which help learn various scales of spectral distributions over multiple frequen…
