SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping

Neural vocoder using denoising diffusion probabilistic model (DDPM) has been improved by adaptation of the diffusion noise distribution to given acoustic features. In this study, we propose SpecGrad that adapts the diffusion noise so that its time-varying spectral envelope becomes close to the conditioning log-mel spectrogram. This adaptation by time-varying filtering improves the sound quality especially in the high-frequency bands. It is processed in the time-frequency domain to keep the computational cost almost the same as the conventional DDPM-based neural vocoders. Experimental results showed that SpecGrad generates higher-fidelity speech waveform than conventional DDPM-based neural vocoders in both analysis-synthesis and speech enhancement scenarios. Audio demos are available at wavegrad.github.io/specgrad/.

Wearable SELD dataset: Dataset for sound event localization and detection using wearable devices around head

Sound event localization and detection (SELD) is a combined task of identifying the sound event and its direction. Deep neural networks (DNNs) are utilized to associate them with the sound signals observed by a microphone array. Although ambisonic microphones are popular in the literature of SELD, they might limit the range of applications due to their predetermined geometry. Some applications (including those for pedestrians that perform SELD while walking) require a wearable microphone array whose geometry can be designed to suit the task. In this paper, for the development of such a wearable SELD, we propose a dataset named Wearable SELD dataset. It consists of data recorded by 24 microphones placed on a head and torso simulators (HATS) with some accessories mimicking wearable devices (glasses, earphones, and headphones). We also provide experimental results of SELD using the proposed dataset and SELDNet to investigate the effect of microphone configuration.

APPLADE: Adjustable Plug-and-play Audio Declipper Combining DNN with Sparse Optimization

In this paper, we propose an audio declipping method that takes advantages of both sparse optimization and deep learning. Since sparsity-based audio declipping methods have been developed upon constrained optimization, they are adjustable and well-studied in theory. However, they always uniformly promote sparsity and ignore the individual properties of a signal. Deep neural network (DNN)-based methods can learn the properties of target signals and use them for audio declipping. Still, they cannot perform well if the training data have mismatches and/or constraints in the time domain are not imposed. In the proposed method, we use a DNN in an optimization algorithm. It is inspired by an idea called plug-and-play (PnP) and enables us to promote sparsity based on the learned information of data, considering constraints in the time domain. Our experiments confirmed that the proposed method is stable and robust to mismatches between training and test data.

Safeguarding test signals for acoustic measurement using arbitrary sounds

We propose a simple method to measure acoustic responses using any sounds by converting them suitable for measurement. This method enables us to use music pieces for measuring acoustic conditions. It is advantageous to measure such conditions without annoying test sounds to listeners. In addition, applying the underlying idea of simultaneous measurement of multiple paths provides practically valuable features. For example, it is possible to measure deviations (temporally stable, random, and time-varying) and the impulse response while reproducing slightly modified contents under target conditions. The key idea of the proposed method is to add relatively small deterministic signals that sound like noise to the original sounds. We call the converted sounds safeguarded test signals.

Objective measurement of pitch extractors' responses to frequency modulated sounds and two reference pitch extraction methods for analyzing voice pitch responses to auditory stimulation

We propose an objective measurement method for pitch extractors' responses to frequency-modulated signals. The method simultaneously measures the linear and the non-linear time-invariant responses and random and time-varying responses. It uses extended time-stretched pulses combined by binary orthogonal sequences. Our recent finding of involuntary voice pitch response to auditory stimulation while voicing motivated this proposal. The involuntary voice pitch response provides means to investigate voice chain subsystems individually and objectively. This response analysis requires reliable and precise pitch extraction. We found that existing pitch extractors failed to correctly analyze signals used for auditory stimulation by using the proposed method. Therefore, we propose two reference pitch extractors based on the instantaneous frequency analysis and multi-resolution power spectrum analysis. The proposed extractors correctly analyze the test signals. We open-sourced MATLAB codes to measure pitch extractors and codes for conducting the voice pitch response experiment on our GitHub repository.

Design of Tight Minimum-Sidelobe Windows by Riemannian Newton's Method

The short-time Fourier transform (STFT), or the discrete Gabor transform (DGT), has been extensively used in signal analysis and processing. Their properties are characterized by a window function, and hence window design is a significant topic up to date. For signal processing, designing a pair of analysis and synthesis windows is important because results of processing in the time-frequency domain are affected by both of them. A tight window is a special window that can perfectly reconstruct a signal by using it for both analysis and synthesis. It is known to make time-frequency-domain processing robust to error, and therefore designing a better tight window is desired. In this paper, we propose a method of designing tight windows that minimize the sidelobe energy. It is formulated as an optimization problem on an oblique manifold, and a Riemannian Newton algorithm on this manifold is derived to efficiently obtain a solution.

Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant Method

Audio source separation is often used as preprocessing of various applications, and one of its ultimate goals is to construct a single versatile model capable of dealing with the varieties of audio signals. Since sampling frequency, one of the audio signal varieties, is usually application specific, the preceding audio source separation model should be able to deal with audio signals of all sampling frequencies specified in the target applications. However, conventional models based on deep neural networks (DNNs) are trained only at the sampling frequency specified by the training data, and there are no guarantees that they work with unseen sampling frequencies. In this paper, we propose a convolution layer capable of handling arbitrary sampling frequencies by a single DNN. Through music source separation experiments, we show that the introduction of the proposed layer enables a conventional audio source separation model to consistently work with even unseen sampling frequencies.

Sparse time-frequency representation via atomic norm minimization

Nonstationary signals are commonly analyzed and processed in the time-frequency (T-F) domain that is obtained by the discrete Gabor transform (DGT). The T-F representation obtained by DGT is spread due to windowing, which may degrade the performance of T-F domain analysis and processing. To obtain a well-localized T-F representation, sparsity-aware methods using $\ell_1$-norm have been studied. However, they need to discretize a continuous parameter onto a grid, which causes a model mismatch. In this paper, we propose a method of estimating a sparse T-F representation using atomic norm. The atomic norm enables sparse optimization without discretization of continuous parameters. Numerical experiments show that the T-F representation obtained by the proposed method is sparser than the conventional methods.

Mixture of orthogonal sequences made from extended time-stretched pulses enables measurement of involuntary voice fundamental frequency response to pitch perturbation

Auditory feedback plays an essential role in the regulation of the fundamental frequency of voiced sounds. The fundamental frequency also responds to auditory stimulation other than the speaker's voice. We propose to use this response of the fundamental frequency of sustained vowels to frequency-modulated test signals for investigating involuntary control of voice pitch. This involuntary response is difficult to identify and isolate by the conventional paradigm, which uses step-shaped pitch perturbation. We recently developed a versatile measurement method using a mixture of orthogonal sequences made from a set of extended time-stretched pulses (TSP). In this article, we extended our approach and designed a set of test signals using the mixture to modulate the fundamental frequency of artificial signals. For testing the response, the experimenter presents the modulated signal aurally while the subject is voicing sustained vowels. We developed a tool for conducting this test quickly and interactively. We make the tool available as an open-source and also provide executable GUI-based applications. Preliminary tests revealed that the proposed method consistently provides compensatory responses with about 100 ms latency, representing involuntary control. Finally, we discuss future applications of the proposed method for objective and non-invasive auditory response measurements.

Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech

Deep neural network (DNN)-based speech enhancement ordinarily requires clean speech signals as the training target. However, collecting clean signals is very costly because they must be recorded in a studio. This requirement currently restricts the amount of training data for speech enhancement less than 1/1000 of that of speech recognition which does not need clean signals. Increasing the amount of training data is important for improving the performance, and hence the requirement of clean signals should be relaxed. In this paper, we propose a training strategy that does not require clean signals. The proposed method only utilizes noisy signals for training, which enables us to use a variety of speech signals in the wild. Our experimental results showed that the proposed method can achieve the performance similar to that of a DNN trained with clean signals.