Ryan Stables

Birmingham City University | BCU · Institute for Digital Experience and Applications

Onset detection is the process of identifying the start points of musical note events within an audio recording. While the detection of percussive onsets is often considered a solved problem, soft onsets-as found in string instrument recordings-still pose a significant challenge for state-of-the-art algorithms. The problem is further exacerbated by...

This meeting report gives an overview of the DAFx 2019 conference held in September 2019 at Birmingham City University, Birmingham, UK. The conference had the same theme as this special issue: digital audio effects. In total, 51 papers were presented at DAFx 2019 either in oral or in poster sessions. The conference had 157 delegates, almost half fr...

Subjective experiments are a cornerstone of modern research, with a variety of tasks being undertaken by subjects. In the field of audio, subjective listening tests provide validation for research and aid fair comparison between techniques or devices such as coding performance, speakers, mixes and source separation systems. Several interfaces have...

Of all music production interfaces, the channel strip with a gain fader and pan pot is likely the most persistent, being found in nearly all digital audio workstations and hardware as the main way to adjust level and stereo position. A popular alternative to the channel strip is the stage view, or stage metaphor, in which the level and stereo posit...

This project presents a web based automatic drum transcription (ADT) system called ADTWeb, which improves on existing systems by automatically generating drum tabulature and enabling web-scale user access. ADTWeb consists of two main stages: i) ADT and ii) monitoring and improvement. The transcription uses pre-trained soft attention mechanism neura...

Zero latency convolution typically uses the Direct Form approach, requiring a large amount of computational resources for every additional sample in the impulse response. A number of methods have been developed to reduce the computational cost of very large signal convolution. However these all introduce latency into the system. In some scenarios t...

Music production is a highly subjective task, which can be difficult to automate. Simple session structures can quickly expose complex mathematical tasks which are difficult to optimise. This paper presents a method for the reduction of masking in an unknown mix using genetic programming. The model uses results from a series of listening tests to g...

Reflecting on a decade of Automatic Mixing systems for multitrack music processing, this paper positions the topic in the wider field of Intelligent Music Production, and seeks to motivate the existing and continued work in this area. Tendencies such as the introduction of machine learning and the increasing complexity of automated systems become a...

Sound engineers typically allocate audio effects to a channel strip in series. This allows the engineer to perform a complex set of operations to fine-tune different tracks in a mixing or mastering environment. In this research, trends in plugin chain selection are investigated, focusing on transformations which modify the timbral characteristics...

In sound production, engineers cascade processing modules at various points in a mix to apply audio effects to channels and busses. Previous studies have investigated the automation of parameter settings based on external semantic cues. In this study, we provide an analysis of the ways in which participants apply full processing chains to musical...

The Web Audio API introduced native audio processing into web browsers. Audio plugin standards have been created for developers to create audio-rich processors and deploy them into media rich websites. It is critical these standards support flexible designs with clear host-plugin interaction to ease integration and avoid non-standard plugins. In...

Music production is a complex process requiring skill and time to undertake. The industry has undergone a digital revolution, but unlike other industries the process has not changed. However, intelligent systems, using the semantic web and signal processing, can reduce this complexity by making certain decisions for the user with minimal interactio...

In this study, we present an online music production tool that facilitates the capture of time-series audio and session data, including action history. This allows us to analyse sessions and infer production decisions based on actions made to the user interface. We conduct an experiment in which mix engineers were asked to use the system to perform...

Spectroscopic diagnostics have been shown to be an effective tool for the analysis and discrimination of disease states from human tissue. Furthermore, Raman spectroscopic probes are of particular interest as they allow for in vivo spectroscopic diagnostics, for tasks such as the identification of tumour margins during surgery. In this study, we in...

In music production, descriptive terminology is used to define perceived sound transformations. By understanding the underlying statistical features associated with these descriptions, we can aid the retrieval of contextually relevant processing parameters using natural language, and create intelligent systems capable of assisting in audio engineer...

In digital audio, software plugins are commonly used to implement audio effects and synthesizers, and integrate them with existing software packages. Whilst these plugins have a number of clearly defined formats, a common standard has not been developed for the web, utilising the Web Audio API. In this paper, we present a standard framework which d...

The Web Audio Evaluation Tool is an open-source, browser-based framework for creating and conducting listening tests. It allows remote deployment, GUI-guided setup, and analysis in the browser. While currently being used for listening tests in various fields, it was initially developed specifically for the study of music production practices. In th...

JS-Xtract is an efficient modular JavaScript library for audio feature extraction, capable of operating on arbitrary time-series data, or being bound to Web Audio objects. The library implements an extensive range of vector and scalar feature extractors, and allows both procedural and object-oriented function calls. We show it performs well across...

The ability to diagnose cancer rapidly with high sensitivity and specificity is essential to exploit advances in new treatments to lead significant reductions in mortality and morbidity. Current cancer diagnostic tests observing tissue architecture and specific protein expression for specific cancers suffer from inter-observer variability, poor det...

Equalisation is one of the most commonly-used tools in sound production, allowing users to control the gains of different frequency components in an audio signal. In this paper we present a model for mapping a set of equalisation parameters to a reduced dimensionality space. The purpose of this approach is to allow a user to interact with the syste...

We present an overview of the Semantic Audio Feature Extraction (SAFE) Project, a novel data collection architecture for the extraction and retrieval of semantic descriptions of musical timbre, deployed within the digital audio workstation. By embedding the data capture system into the music production workflow, we are able to max-imise the return...

INTRODUCTION: Complete tumour removal during surgery is one of the primary factors for recurrence-free survival. The current process is unable to accurately identify tumour margins and data feedback takes too long for responsive action during surgery. Our recent study has shown the ability of Raman spectroscopy to distinguish between metastatic bra...

In this study we investigate ways in which data sonification can improve standard data analysis techniques currently employed in the analysis of stem-cells using Fourier Transform Infrared (FTIR) Spectroscopy. Four different sonification methods have been eval-uated and their effectiveness has been evaluated through listen-ing tests, designed to as...

In this study we discuss some of the limitations of Gaussian humanisation and consider ways in which the articulation patterns exhibited by percussionists can be emulated using a probabilistic model. Prior and likelihood functions are derived from a dataset of professional drummers to create a series of empirical distributions. These are then used...

A model is presented for the analysis and synthesis of low frequency human-like pitch deviation, as a replacement for existing modulation techniques in singing voice synthesis systems. Fundamental frequency (f 0) measurements are taken from vocalists producing a selected range of utterances without vibrato and trends in the data are observed. A pro...

In this study, we evaluate current techniques for drum pattern humanisation and suggest new methods using a probabilistic model. Our statistical analysis shows that both deviations from a fixed grid and corresponding amplitude values of drum patterns can have non-Gaussian distributions with underlying temporal structures. We plot distributions and...

Using commodity computers in conjunction with live music digital audio workstations (DAW) has become increasingly more popular in recent years. The latency of these DAW audio processing chains for some application such as live audio monitoring has always been perceived as a problem when DSP audio effects are needed. With "High Definition Audio" bei...

We present a model for the generation of low frequency human-like pitch deviation. We take f0 measurements from vocalists producing a 300Hz fixed tone without vibrato and find that smaller regions are evident, each with Quasi-Gaussian distributions. We present a function to implement this with a PSOLA pitch shifting algorithm, providing natural sou...

A model is presented for the analysis and synthesis of low frequency human-like pitch deviation, as a replacement for existing modulation techniques in singing voice syn-thesis systems. We build on research taken from [1], in or-der to find the features of drift under selected conditions in singing. Fundamental Frequency (f 0) measurements are take...