Music source separation is the task of separating musical sources from an audio mixture. It has various direct applications including automatic karaoke generation, enhancing musical recordings, and 3D-audio upmixing; but also has implications for other downstream music information retrieval tasks such as multi-instrument transcription. However, the majority of research has focused on fixed stem separation of vocals, drums, and bass stems. While such models have highlighted capabilities of source separation using deep learning, their implications are limited to very few use cases. Such models are unable to separate most other instruments due to insufficient training data. Moreover, class-based separation inherently limits the applicability of such models to be unable to separate monotimbral mixtures. This thesis focuses on separating musical sources without requiring timbral distinction among the sources. Preliminary attempts focus on the separation of vocal harmonies from choral ensembles using ...

When listening to music, some humans can easily recognize which instruments play at what time or when a new musical segment starts, but cannot describe exactly how they do this. To automatically describe particular aspects of a music piece – be it for an academic interest in emulating human perception, or for practical applications –, we can thus not directly replicate the steps taken by a human. We can, however, exploit that humans can easily annotate examples, and optimize a generic function to reproduce these annotations. In this thesis, I explore solving different music perception tasks with deep learning, a recent branch of machine learning that optimizes functions of many stacked nonlinear operations – referred to as deep neural networks – and promises to obtain better results or require less domain knowledge than more traditional techniques. In particular, I employ ...

Everyday sounds in real-world environments are a powerful source of information by which humans can interact with their environments. Humans can infer what is happening around them by listening to everyday sounds. At the same time, it is a challenging task for a computer algorithm in a smart device to automatically recognise, understand, and interpret everyday sounds. Sound event detection (SED) is the process of transcribing an audio recording into sound event tags with onset and offset time values. This involves classification and segmentation of sound events in the given audio recording. SED has numerous applications in everyday life which include security and surveillance, automation, healthcare monitoring, multimedia information retrieval, and assisted living technologies. SED is to everyday sounds what automatic speech recognition (ASR) is to speech and automatic music transcription (AMT) is to music. The fundamental questions in designing ...

In the early days of speech synthesis research, understanding voice production has attracted the attention of scientists with the goal of producing intelligible speech. Later, the need to produce more natural voices led researchers to use prerecorded voice databases, containing speech units, reassembled by a concatenation algorithm. With the outgrowth of computer capacities, the length of units increased, going from diphones to non-uniform units, in the so-called unit selection framework, using a strategy referred to as 'take the best, modify the least'. Today the new challenge in voice synthesis is the production of expressive speech or singing. The mainstream solution to this problem is based on the “there is no data like more data” paradigm: emotionspecific databases are recorded and emotion-specific units are segmented. In this thesis, we propose to restart the expressive speech synthesis problem, from its original voice ...

This thesis focuses on the development of automatic accompaniment sys- tems. We investigate previous systems and look at a range of approaches that have been attempted for the problem of beat tracking. Most beat trackers are intended for the purposes of music information retrieval where a ‘black box’ approach is tested on a wide variety of music genres. We highlight some of the difficulties facing offline beat trackers and design a new approach for the problem of real-time drum tracking, developing a system, B-Keeper, which makes reasonable assumptions on the nature of the signal and is provided with useful prior knowledge. Having developed the system with offline studio recordings, we look to test the system with human players. Existing offline evaluation methods seem less suitable for a performance system, since we also wish to evaluate the interaction between musician and ...

This thesis focuses on the development of paradigms and techniques for the design and implementation of multimodal interactive systems, mainly for performing arts applications. The work addresses research issues in the fields of human-computer interaction, multimedia systems, and sound and music computing. The thesis is divided into two parts. In the first one, after a short review of the state-of-the-art, the focus moves on the definition of environments in which novel forms of technology-integrated artistic performances can take place. These are distributed active mixed reality environments in which information at different layers of abstraction is conveyed mainly non-verbally through expressive gestures. Expressive gesture is therefore defined and the internal structure of a virtual observer able to process it (and inhabiting the proposed environments) is described in a multimodal perspective. The definition of the structure of the environments, of the virtual ...

In the world of Information and communications technology (ICT), strategies for innovation and development are increasingly focusing on applications that require spatial representation and real-time interaction with and within 3D-media environments. One of the major challenges that such applications have to address is user-centricity, reflecting e.g. on developing complexity-hiding services so that people can personalize their own delivery of services. In these terms, multimodal interfaces represent a key factor for enabling an inclusive use of new technologies by everyone. In order to achieve this, multimodal realistic models that describe our environment are needed, and in particular models that accurately describe the acoustics of the environment and communication through the auditory modality are required. Examples of currently active research directions and application areas include 3DTV and future internet, 3D visual-sound scene coding, transmission and reconstruction and teleconferencing systems, to name but ...

Recent years have witnessed a significant interest in interpretable machine learning (IML) research that develops techniques to analyse machine learning (ML) models. Understanding ML models is essential to gain trust in their predictions and to improve datasets, model architectures and training techniques. The majority of effort in IML research has been in analysing models that classify images or structured data and comparatively less work exists that analyses models for other domains. This research focuses on developing novel IML methods and on extending existing methods to understand machine listening models that analyse audio. In particular, this thesis reports the results of three studies that apply three different IML methods to analyse five singing voice detection (SVD) models that predict singing voice activity in musical audio excerpts. The first study introduces SoundLIME (SLIME), a method to generate temporal, spectral or time-frequency explanations ...

It takes more time to think of a silent scene, action or event than finding one that emanates sound. Not only speaking or playing music but almost everything that happens is accompanied with or results in one or more sounds mixed together. This makes acoustic event detection (AED) one of the most researched topics in audio signal processing nowadays and it will probably not see a decline anywhere in the near future. This is due to the thirst for understanding and digitally abstracting more and more events in life via the enormous amount of recorded audio through thousands of applications in our daily routine. But it is also a result of two intrinsic properties of audio: it doesn’t need a direct sight to be perceived and is less intrusive to record when compared to image or video. Many applications such ...

Music is built from sound, ultimately resulting from an elaborate interaction between the sound-generating properties of physical objects (i.e. music instruments) and the sound perception abilities of the human auditory system. Humans, even without any kind of formal music training, are typically able to ex- tract, almost unconsciously, a great amount of relevant information from a musical signal. Features such as the beat of a musical piece, the main melody of a complex musical ar- rangement, the sound sources and events occurring in a complex musical mixture, the song structure (e.g. verse, chorus, bridge) and the musical genre of a piece, are just some examples of the level of knowledge that a naive listener is commonly able to extract just from listening to a musical piece. In order to do so, the human auditory system uses a variety of cues ...

The growing risk of privacy violation and espionage associated with the rapid spread of mobile communications renewed interest in the original concept of sending encrypted voice as audio signal over arbitrary voice channels. The usual methods used for encrypted data transmission over analog telephony turned out to be inadequate for modern vocal links (cellular networks, VoIP) equipped with voice compression, voice activity detection, and adaptive noise suppression algorithms. The limited available bandwidth, nonlinear channel distortion, and signal fadings motivate the investigation of a dedicated, joint approach for speech encoding and encryption adapted to modern noisy voice channels. This thesis aims to develop, analyze, and validate secure and efficient schemes for real-time speech encryption and transmission via modern voice channels. In addition to speech encryption, this study covers the security and operational aspects of the whole voice communication system, as this ...

This thesis addresses the development of a system for pitch-informed solo and accompaniment separation capable of separating main instruments from music accompaniment regardless of the musical genre of the track, or type of music accompaniment. For the solo instrument, only pitched monophonic instruments were considered in a single-channel scenario where no panning or spatial location information is available. In the proposed method, pitch information is used as an initial stage of a sinusoidal modeling approach that attempts to estimate the spectral information of the solo instrument from a given audio mixture. Instead of estimating the solo instrument on a frame by frame basis, the proposed method gathers information of tone objects to perform separation. Tone-based processing allowed the inclusion of novel processing stages for attack re nement, transient interference reduction, common amplitude modulation (CAM) of tone objects, and for better ...

Automatic speaker recognition is the use of a machine to identify an individual from a spoken sentence. Recently, this technology has been undergone an increasing use in applications such as access control, transaction authentication, law enforcement, forensics, and system customisation, among others. One of the central questions addressed by this field is what is it in the speech signal that conveys speaker identity. Traditionally, automatic speaker recognition systems have relied mostly on short-term features related to the spectrum of the voice. However, human speaker recognition relies on other sources of information; therefore, there is reason to believe that these sources can play also an important role in the automatic speaker recognition task, adding complementary knowledge to the traditional spectrum-based recognition systems and thus improving their accuracy. The main objective of this thesis is to add prosodic information to a traditional ...

This thesis faces the problem of automatically classifying environmental sounds, i.e., any non-speech or non-music sounds that can be found in the environment. Broadly speaking, two main processes are needed to perform such classification: the signal feature extraction so as to compose representative sound patterns and the machine learning technique that performs the classification of such patterns. The main focus of this research is put on the former, studying relevant signal features that optimally represent the sound characteristics since, according to several references, it is a key issue to attain a robust recognition. This type of audio signals holds many differences with speech or music signals, thus specific features should be determined and adapted to their own characteristics. In this sense, new signal features, inspired by the human auditory system and the human perception of sound, are proposed to improve ...

Cross-lingual voice conversion refers to the automatic transformation of a source speaker’s voice to a target speaker’s voice in a language that the target speaker can not speak. It involves a set of statistical analysis, pattern recognition, machine learning, and signal processing techniques. This study focuses on the problems related to cross-lingual voice conversion by discussing open research questions, presenting new methods, and performing comparisons with the state-of-the-art techniques. In the training stage, a Phonetic Hidden Markov Model based automatic segmentation and alignment method is developed for cross-lingual applications which support textindependent and text-dependent modes. Vocal tract transformation function is estimated using weighted speech frame mapping in more detail. Adjusting the weights, similarity to target voice and output quality can be balanced depending on the requirements of the cross- lingual voice conversion application. A context-matching algorithm is developed to reduce ...