The synthesis of sound via deep learning methods has recently received much attention. Some problems for deep learning approaches to sound synthesis relate to the amount of data needed to specify an audio signal and the necessity of preserving both the long and short time coherence of the synthesised signal. Visual time-frequency representations such as the log-mel-spectrogram have gained in popularity. The log-mel-spectrogram is a perceptually informed representation of audio that greatly compresses the amount of information required for the description of the sound. However, because of this compression, this representation is not directly invertible. Both signal processing and machine learning techniques have previously been applied to the inversion of the log-mel-spectrogram but they both caused audible distortions in the synthesized sounds due to issues of temporal and spectral coherence. In this paper, we outline the application of a sinusoidal model to the inversion of the log-mel-spectrogram for pitched musical instrument sounds outperforming state-of-the-art deep learning methods. The approach could be later used as a general decoding step from spectral to time intervals in neural applications.
UBTECH Robotics Corporate（优必选机器人公司）；Novosibirsk State University（新西伯利亚国立大学）
In speech synthesis and speech enhancement systems, melspectrograms need to be precise in acoustic representations. However, the generated spectrograms are over-smooth, that could not produce high quality synthesized speech. Inspired by image-to-image translation, we address this problem by using a learning-based post filter combining Pix2PixHD and ResUnet to reconstruct the mel-spectrograms together with super-resolution. From the resulting super-resolution spectrogram networks, we can generate enhanced spectrograms to produce high quality synthesized speech. Our proposed model achieves impro…
Most recent speech synthesis systems are composed of a synthesizer and a vocoder. However, the existing synthesizers and vocoders can only be matched to acoustic features extracted with a specific configuration. Hence, we can't combine arbitrary synthesizers and vocoders together to form a complete system, not to mention apply to a newly developed model. In this paper, we proposed Universal Adaptor, which takes a Mel-spectrogram parametrized by the source configuration and converts it into a Mel-spectrogram parametrized by the target configuration, as long as we feed in the source and the targ…
NTT Communication Science Laboratories, NTT Corporation（日本电信电话株式会社通信科学实验室）
In recent text-to-speech synthesis and voice conversion systems, a mel-spectrogram is commonly applied as an intermediate representation, and the necessity for a mel-spectrogram vocoder is increasing. A mel-spectrogram vocoder must solve three inverse problems: recovery of the original-scale magnitude spectrogram, phase reconstruction, and frequency-to-time conversion. A typical convolutional mel-spectrogram vocoder solves these problems jointly and implicitly using a convolutional neural network, including temporal upsampling layers, when directly calculating a raw waveform. Such an approach …
Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation
Beijing University of Posts and Telecommunications（北京邮电大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beijing National Research Center for Information Science and Technology, Tsinghua University（清华大学北京信息科学与技术国家研究中心）；Tencent AI Lab（腾讯AI实验室）
CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR
Zhejiang University（浙江大学）；Westlake University（西湖大学）；School of Engineering（工程学院）；Institute of Advanced Technology（先进技术研究院）；Westlake Institute for Advanced Study（西湖研究学院）
We describe our approach for the generative emotional vocal burst task (ExVo Generate) of the ICML Expressive Vocalizations Competition. We train a conditional StyleGAN2 architecture on mel-spectrograms of preprocessed versions of the audio samples. The mel-spectrograms generated by the model are then inverted back to the audio domain. As a result, our generated samples substantially improve upon the baseline provided by the competition from a qualitative and quantitative perspective for all emotions. More precisely, even for our worst-performing emotion (awe), we obtain an FAD of 1.76 compare…
Most neural vocoders employ band-limited mel-spectrograms to generate waveforms. If full-band spectral features are used as the input, the vocoder can be provided with as much acoustic information as possible. However, in some models employing full-band mel-spectrograms, an over-smoothing problem occurs as part of which non-sharp spectrograms are generated. To address this problem, we propose UnivNet, a neural vocoder that synthesizes high-fidelity waveforms in real time. Inspired by works in the field of voice activity detection, we added a multi-resolution spectrogram discriminator that empl…
Speech synthesis is widely used in many practical applications. In recent years, speech synthesis technology has developed rapidly. However, one of the reasons why synthetic speech is unnatural is that it often has over-smoothness. In order to improve the naturalness of synthetic speech, we first extract the mel-spectrogram of speech and convert it into a real image, then take the over-smooth mel-spectrogram image as input, and use image-to-image translation Generative Adversarial Networks(GANs) framework to generate a more realistic mel-spectrogram. Finally, the results show that this method …
Faculty of Electrical Engineering, University of Montenegro（黑山大学电气工程学院）
The paper addresses acoustic vehicle detection and speed estimation from single sensor measurements. We predict the vehicle's pass-by instant by minimizing clipped vehicle-to-microphone distance, which is predicted from the mel-spectrogram of input audio, in a supervised learning approach. In addition, mel-spectrogram-based features are used directly for vehicle speed estimation, without introducing any intermediate features. The results show that the proposed features can be used for accurate vehicle detection and speed estimation, with an average error of 7.87 km/h. If we formulate speed est…
NTT Communication Science Laboratories, NTT Corporation（NTT（日本电报电话公司）通信科学实验室）
Non-parallel voice conversion (VC) is a technique for learning mappings between source and target speeches without using a parallel corpus. Recently, cycle-consistent adversarial network (CycleGAN)-VC and CycleGAN-VC2 have shown promising results regarding this problem and have been widely used as benchmark methods. However, owing to the ambiguity of the effectiveness of CycleGAN-VC/VC2 for mel-spectrogram conversion, they are typically used for mel-cepstrum conversion even when comparative methods employ mel-spectrogram as a conversion target. To address this, we examined the applicability of…
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 coarser scale mel-spectrograms that capture the suprasegmental information in speech, and later uses these coarser scale mel-spectrograms to predict finer scale mel-spectrograms capturing fine-grained prosody. We present details for two specific versions of MSS called Word-level MSS and Sentence-level MSS where the scales in our system are motivated by the ling…
We propose a technique to compute spectrograms using Frequency Domain Linear Prediction (FDLP) that uses all-pole models to fit the squared Hilbert envelope of speech in different frequency sub-bands. The spectrogram of a complete speech utterance is computed by overlap-add of contiguous all-pole model responses. A long context window of 1.5 seconds allows us to capture the low frequency temporal modulations of speech in the spectrogram. For an end-to-end automatic speech recognition task, the FDLP spectrogram performs on par with the standard mel spectrogram features for clean read speech tra…
In this paper, we describe our contribution to Task 2 of the DCASE 2018 Audio Challenge. While it has become ubiquitous to utilize an ensemble of machine learning methods for classification tasks to obtain better predictive performance, the majority of ensemble methods combine predictions rather than learned features. We propose a single-model method that combines learned high-level features computed from log-scaled mel-spectrograms and raw audio data. These features are learned separately by two Convolutional Neural Networks, one for each input type, and then combined by densely connected lay…
In this paper, we propose to unify the two aspects of voice synthesis, namely text-to-speech (TTS) and vocoder, into one framework based on a pair of forward and reverse-time linear stochastic differential equations (SDE). The solutions of this SDE pair are two stochastic processes, one of which turns the distribution of mel spectrogram (or wave), that we want to generate, into a simple and tractable distribution. The other is the generation procedure that turns this tractable simple signal into the target mel spectrogram (or wave). The model that generates mel spectrogram is called ItôTTS, an…
Aalto University（阿尔托大学）；National Institute of Informatics（国立信息学研究所）；University of Edinburgh（爱丁堡大学）
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 modeling, but present additional challenges for vocoding (i.e., waveform generation from the acoustic features). High-quality synthesis can be achieved with neural vocoders, such as WaveNet, but such autoregressive models suffer from slow sequential inference. Meanwhile, their existing parallel inference counterparts are difficult to train and require increas…
Singapore University of Technology and Design（新加坡科技设计大学）
This paper thoroughly analyses the effect of different input representations on polyphonic multi-instrument music transcription. We use our own GPU based spectrogram extraction tool, nnAudio, to investigate the influence of using a linear-frequency spectrogram, log-frequency spectrogram, Mel spectrogram, and constant-Q transform (CQT). Our results show that a $8.33$% increase in transcription accuracy and a $9.39$% reduction in error can be obtained by choosing the appropriate input representation (log-frequency spectrogram with STFT window length 4,096 and 2,048 frequency bins in the spectrog…
Analysing music in the field of machine learning is a very difficult problem with numerous constraints to consider. The nature of audio data, with its very high dimensionality and widely varying scales of structure, is one of the primary reasons why it is so difficult to model. There are many applications of machine learning in music, like the classifying the mood of a piece of music, conditional music generation, or popularity prediction. The goal for this project was to develop a genre-conditional generative model of music based on Mel spectrograms and evaluate its performance by comparing i…
Federal University of Technology – Paraná（巴拉那联邦理工大学）；University of Campinas（坎皮纳斯大学）
In this work, we analyse the random projections of Mel-spectrograms as low-level features for music genre classification. This approach was compared to handcrafted features, features learned using an auto-encoder and features obtained from a transfer learning setting. Tests in five different well-known, publicly available datasets show that random projections leads to results comparable to learned features and outperforms features obtained via transfer learning in a shallow learning scenario. Random projections do not require using extensive specialist knowledge and, simultaneously, requires l…
In this paper, we propose a novel neural network model called KaraSinger for a less-studied singing voice synthesis (SVS) task named score-free SVS, in which the prosody and melody are spontaneously decided by machine. KaraSinger comprises a vector-quantized variational autoencoder (VQ-VAE) that compresses the Mel-spectrograms of singing audio to sequences of discrete codes, and a language model (LM) that learns to predict the discrete codes given the corresponding lyrics. For the VQ-VAE part, we employ a Connectionist Temporal Classification (CTC) loss to encourage the discrete codes to carry…
For training the sequence-to-sequence voice conversion model, we need to handle an issue of insufficient data about the number of speech pairs which consist of the same utterance. This study experimentally investigated the effects of Mel-spectrogram augmentation on training the sequence-to-sequence voice conversion (VC) model from scratch. For Mel-spectrogram augmentation, we adopted the policies proposed in SpecAugment. In addition, we proposed new policies (i.e., frequency warping, loudness and time length control) for more data variations. Moreover, to find the appropriate hyperparameters o…
Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from the mel-spectrogram using vocoder such as WaveNet. Compared with traditional concatenative and statistical parametric approaches, neural network based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust (i.e., some words are skipped or repeated) and lack of controllability (voice speed or prosody control). In this w…
Graduate School of Culture Technology, KAIST（韩国科学技术院文化技术研究生院）
Singing voice separation (SVS) is a task that separates singing voice audio from its mixture with instrumental audio. Previous SVS studies have mainly employed the spectrogram masking method which requires a large dimensionality in predicting the binary masks. In addition, they focused on extracting a vocal stem that retains the wet sound with the reverberation effect. This result may hinder the reusability of the isolated singing voice. This paper addresses the issues by predicting mel-spectrogram of dry singing voices from the mixed audio as neural vocoder features and synthesizing the singi…
Along with the evolution of music technology, a large number of styles, or "subgenres," of Electronic Dance Music(EDM) have emerged in recent years. While the classification task of distinguishing between EDM and non-EDM has been often studied in the context of music genre classification, little work has been done on the more challenging EDM subgenre classification. The state-of-art model is based on extremely randomized trees and could be improved by deep learning methods. In this paper, we extend the state-of-art music auto-tagging model "short-chunkCNN+Resnet" to EDM subgenre classification…
In audio processing applications, the generation of expressive sounds based on high-level representations demonstrates a high demand. These representations can be used to manipulate the timbre and influence the synthesis of creative instrumental notes. Modern algorithms, such as neural networks, have inspired the development of expressive synthesizers based on musical instrument timbre compression. Unsupervised deep learning methods can achieve audio compression by training the network to learn a mapping from waveforms or spectrograms to low-dimensional representations. This study investigates…
ESTVocoder: An Excitation-Spectral-Transformed Neural Vocoder Conditioned on Mel Spectrogram
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）；University of Science and Technology of China（中国科学技术大学）
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
Pattern recognition from audio signals is an active research topic encompassing audio tagging, acoustic scene classification, music classification, and other areas. Spectrogram and mel-frequency cepstral coefficients (MFCC) are among the most commonly used features for audio signal analysis and classification. Recently, deep convolutional neural networks (CNN) have been successfully used for audio classification problems using spectrogram-based 2D features. In this paper, we present SpectNet, an integrated front-end layer that extracts spectrogram features within a CNN architecture that can be…
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…
Vocoders are models capable of transforming a low-dimensional spectral representation of an audio signal, typically the mel spectrogram, to a waveform. Modern speech generation pipelines use a vocoder as their final component. Recent vocoder models developed for speech achieve a high degree of realism, such that it is natural to wonder how they would perform on music signals. Compared to speech, the heterogeneity and structure of the musical sound texture offers new challenges. In this work we focus on one specific artifact that some vocoder models designed for speech tend to exhibit when appl…
Beijing Bombax XiaoIce Technology Co., Ltd（北京木棉小冰科技有限公司）；National Institute of Informatics（国立信息学研究所）；SOKENDAI（综合研究大学院大学）
XiaoiceSing is a singing voice synthesis (SVS) system that aims at generating 48kHz singing voices. However, the mel-spectrogram generated by it is over-smoothing in middle- and high-frequency areas due to no special design for modeling the details of these parts. In this paper, we propose XiaoiceSing2, which can generate the details of middle- and high-frequency parts to better construct the full-band mel-spectrogram. Specifically, in order to alleviate this problem, XiaoiceSing2 adopts a generative adversarial network (GAN), which consists of a FastSpeech-based generator and a multi-band dis…
We apply the vision transformer, a deep machine learning model build around the attention mechanism, on mel-spectrogram representations of raw audio recordings. When adding mel-based data augmentation techniques and sample-weighting, we achieve comparable performance on both (PRS and CCS challenge) tasks of ComParE21, outperforming most single model baselines. We further introduce overlapping vertical patching and evaluate the influence of parameter configurations. Index Terms: audio classification, attention, mel-spectrogram, unbalanced data-sets, computational paralinguistics
Duke University（杜克大学）；University of Minnesota Twin Cities（明尼苏达大学双城分校）
Speech Emotion Recognition (SER) has emerged as a critical component of the next generation human-machine interfacing technologies. In this work, we propose a new dual-level model that predicts emotions based on both MFCC features and mel-spectrograms produced from raw audio signals. Each utterance is preprocessed into MFCC features and two mel-spectrograms at different time-frequency resolutions. A standard LSTM processes the MFCC features, while a novel LSTM architecture, denoted as Dual-Sequence LSTM (DS-LSTM), processes the two mel-spectrograms simultaneously. The outputs are later average…
