Stencil operations are often a key component when performing acoustics simulations, for which the specific choice of implementation can have a significant effect on both accuracy and computational performance. This paper presents a detailed investigation of computational performance for GPU-based stencil operations in two-step finite difference schemes, using stencils of varying shape and size (ranging from seven to more than 450 points in size). Using an Nvidia K20 GPU, it is found that as the stencil size increases, compute times increase less than that naively expected by considering only the number of computational operations involved, because performance is instead determined by data transfer times throughout the GPU memory architecture. With regards to the effects of stencil shape, performance obtained with stencils that are compact in space is mainly due to efficient use of the read-only data (texture) cache on the K20, and performance obtained with standard high-order stencils is due to increased memory bandwidth usage, compensating for lower cache hit rates. Also in this study, a brief comparison is made with performance results from a related, recent study that used a shared memory approach on a GTX 670 GPU device. It is found that by making efficient use of a GTX 660Ti GPU—whose computational performance is generally lower than that of a GTX 670—similar or better performance to those results can be achieved without the use of shared memory.

Download

In this paper a system for vowel conversion between different speakers using short-time speech segments is presented. The input speech signal is segmented into period-length speech segments whose fundamental frequency and first two formants are used to find the perceivable vowel-quality. These segments are used to represent a voiced phoneme, i.e. a vowel. The approach relies on pitchsynchronous analysis and uses a modified PSOLA technique for concatenation of the vowel segments. Vowel conversion between speakers is achieved by exchanging the phonetic constituents of a source speaker’s speech waveform in voiced regions of speech whilst preserving prosodic features of the source speaker, thus introducing a method for phonetic segmentation, mapping, and reconstruction of vowels.

Download

The APEX system [1] enables vocal tract articulation using a reduced set of user controllable parameters by means of Principal Component Analysis of X-ray tract data. From these articulatory profiles it is then possible to calculate cross-sectional area function data that can be used as input to a number of articulatory based speech synthesis algorithms. In this paper the Kelly-Lochbaum 1-D digital waveguide vocal tract is used, and both APEX control and synthesis engine have been implemented and tested in SuperCollider. Accurate formant synthesis and real-time control are demonstrated, although for multi-parameter speech-like articulation a more direct mapping from tract-to-synthesizer tube sections is needed. SuperCollider provides an excellent framework for the further exploration of this work.

Download

We present a method for mapping between the input space of a parametric equaliser and a lower-dimensional representation, whilst preserving the effect’s dependency on the incoming audio signal. The model consists of a parameter weighting stage in which the parameters are scaled to spectral features of the audio signal, followed by a mapping process, in which the equaliser’s 13 inputs are converted to (x, y) coordinates. The model is trained with parameter space data representing two timbral adjectives (warm and bright), measured across a range of musical instrument samples, allowing users to impose a semantically-meaningful timbral modification using the lower-dimensional interface. We test 10 mapping techniques, comprising of dimensionality reduction and reconstruction methods, and show that a stacked autoencoder algorithm exhibits the lowest parameter reconstruction variance, thus providing an accurate map between the input and output space. We demonstrate that the model provides an intuitive method for controlling the audio effect’s parameter space, whilst accurately reconstructing the trajectories of each parameter and adapting to the incoming audio spectrum.

Download

The measurement of perceived loudness is a difficult yet important task with a multitude of applications such as loudness alignment of complex stimuli and loudness restoration for the hearing impaired. Although computational hearing models exist, few are able to accurately predict the binaural loudness of everyday sounds. Such models demand excessive processing power making real-time loudness metering problematic. In this work, the dynamic auditory loudness models of Glasberg and Moore (J. Audio Eng. Soc., 2002) and Chen and Hu (IEEE ICASSP, 2012) are presented, extended and realised as binaural loudness meters. The performance bottlenecks are identified and alleviated by reducing the complexity of the excitation transformation stages. The effects of three parameters (hop size, spectral compression and filter spacing) on model predictions are analysed and discussed within the context of features used by scientists and engineers to quantify and monitor the perceived loudness of music and speech. Parameter values are presented and perceptual implications are described.

Download

Augmented audification has recently been introduced as a method that blends between audification and an auditory graph. Advantages of both standard methods of sonification are preserved. The effectivity of the method is shown in this paper by the example of random time series. Just noticeable kurtosis differences are effected positively by the new method as compared to pure audification. Furthermore, skewness can be made audible.

Download

The dance music genres of hardcore, jungle and drum & bass (HJDB) emerged in the United Kingdom during the early 1990s as a result of affordable consumer sampling technology and the popularity of rave music and culture. A key attribute of these genres is their usage of fast-paced drums known as breakbeats. Automated analysis of breakbeat usage in HJDB would allow for novel digital audio effects and musicological investigation of the genres. An obstacle in this regard is the automated identification of breakbeats used in HJDB music. This paper compares three strategies for breakbeat detection: (1) a generalised frame-based music classification scheme; (2) a specialised system that segments drums from the audio signal and labels them with an SVM classifier; (3) an alternative specialised approach using a deep network classifier. The results of our evaluations demonstrate the superiority of the specialised approaches, and highlight the need for style-specific workflows in the determination of particular musical attributes in idiosyncratic genres. We then leverage the output of the breakbeat classification system to produce an automated breakbeat sequence reconstruction, ultimately recreating the HJDB percussion arrangement.

Download

Serious games can be used for training orientation and mobility skills of visually impaired children and youngsters. Here we present a serious game for training sound localization skills and concepts usually covered at orientation and mobility classes, such as front/back and left/right. In addition, the game helps the players to train simple body rotation mobility skills. The game was designed for touch screen mobile devices and has an audio virtual environment created with 3D spatialized audio obtained with head-related transfer functions. The results from a usability test with blind students show that the game can have a positive impact on the players’ skills, namely on their motor coordination and localization skills, as well as on their self-confidence.

Download

This paper describes the implementation of a recently introduced parallel graphic equalizer (PGE) in a heterogeneous way. The control and audio signal processing parts of the PGE are distributed to a PC and to a signal processor, of WaveCore architecture, respectively. This arrangement is particularly suited to the algorithm in question, benefiting from the low-latency characteristics of the audio signal processor as well as general purpose computing power for the more demanding filter coefficient computation. The design is achieved cleanly in a high-level language called Kronos, which we have adapted for the purposes of heterogeneous code generation from a uniform program source.

Download

Nonstationary oscillations are ubiquitous in music and speech, ranging from the fast transients in the attack of musical instruments and consonants to amplitude and frequency modulations in expressive variations present in vibrato and prosodic contours. Modeling nonstationary oscillations with sinusoids remains one of the most challenging problems in signal processing because the fit also depends on the nature of the underlying sinusoidal model. For example, frequency modulated sinusoids are more appropriate to model vibrato than fast transitions. In this paper, we propose to model nonstationary oscillations with adaptive sinusoids from the extended adaptive quasi-harmonic model (eaQHM). We generated synthetic nonstationary sinusoids with different amplitude and frequency modulations and compared the modeling performance of adaptive sinusoids estimated with eaQHM, exponentially damped sinusoids estimated with ESPRIT, and log-linear-amplitude quadratic-phase sinusoids estimated with frequency reassignment. The adaptive sinusoids from eaQHM outperformed frequency reassignment for all nonstationary sinusoids tested and presented performance comparable to exponentially damped sinusoids.

Download