Cochlear implants (CI) are surgically implanted hearing aids that provide auditory sensations to deaf people through direct electrical stimulation of the auditory nerve. Although relatively good speech understanding can be achieved by implanted subjects, pitch perception by CI subjects is about 50 times worse than observed for normal-hearing (NH) persons. Pitch is, however, important for intonation, music, speech understanding in tonal languages, and for separating multiple simultaneous sound sources. The major goal of this work is to improve pitch perception by CI subjects. In CI subjects two fundamental mechanisms are used for pitch perception: place pitch and temporal pitch. Our results show that place pitch is correlated to the sound¢s brightness because place pitch sensation is related to the centroid of the excitation pattern along the cochlea. The slopes of the excitation pattern determine place pitch sensitivity. Our results also ...

Cochlear implants (CIs) aim to restore hearing in severely to profoundly deaf adults, children and infants. Electrically evoked auditory steady-state responses (EASSRs) are neural responses to continuous modulated pulse trains, and can be objectively detected at the modulation frequency in the electro-encephalogram (EEG). EASSRs provide a number of advantages over other objective measures, because frequency-specific stimuli are used, because targeted brain areas can be studied, depending on the chosen stimulation parameters, and because they can objectively be detected using statistical methods. EASSRs can potentially be used to determine appropriate stimulation levels during CI fitting, without behavioral input from the subjects. Furthermore, speech understanding in noise varies greatly between CI subjects. EASSRs lend themselves well to study the underlying causes of this variability, such as the integrity of the electrode-neuron interface or changes in the auditory cortex following deafness and following ...

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 ...

The production and delivery of audio for television involve many creative and technical challenges. One of them is concerned with the level balance between the foreground speech (also referred to as dialogue) and the background elements, e.g., music, sound effects, and ambient sounds. Background elements are fundamental for the narrative and for creating an engaging atmosphere, but they can mask the dialogue, which the audience wishes to follow in a comfortable way. Very different individual factors of the people in the audience clash with the creative freedom of the content creators. As a result, service providers receive regular complaints about difficulties in understanding the dialogue because of too loud background sounds. While this has been a known issue for at least three decades, works analyzing the problem and up-to-date statics were scarce before the contributions in this work. Enabling the ...

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 ...

In digital speech-communication systems like mobile phones, public address systems and hearing aids, conveying the message is one of the most important goals. This can be challenging since the intelligibility of the speech may be harmed at various stages before, during and after the transmission process from sender to receiver. Causes which create such adverse conditions include background noise, an unreliable internet connection during a Skype conversation or a hearing impairment of the receiver. To overcome this, many speech-communication systems include speech processing algorithms to compensate for these signal degradations like noise reduction. To determine the effect on speech intelligibility of these signal processing based solutions, the speech signal has to be evaluated by means of a listening test with human listeners. However, such tests are costly and time consuming. As an alternative, reliable and fast machine-driven intelligibility predictors are ...

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 ...

Using a hearing device is one of the most successful approaches to partially restore the degraded functionality of an impaired auditory system. However, due to the complex structure of the human auditory system, hearing impairment can manifest itself in different ways and, therefore, its compensation can be achieved through different classes of hearing devices. Although the majority of hearing devices consists of conventional hearing aids (HAs), several other classes of hearing devices have been developed. For instance, bone-conduction devices (BCDs) and cochlear implants (CIs) have successfully been used for more than thirty years. More recently, other classes of implantable devices have been developed such as middle ear implants (MEIs), implantable BCDs, and direct acoustic cochlear implants (DACIs). Most of these different classes of hearing devices rely on a sound processor running different algorithms able to compensate for the hearing impairment. ...

One in five experiences hearing loss. The World Health Organization estimates that this number will increase to one in four in 2050. Luckily, effective hearing devices such as hearing aids and cochlear implants exist with advanced speaker enhancement algorithms that can significantly improve the quality of life of people suffering from hearing loss. State-of-the-art hearing devices, however, underperform in a so-called `cocktail party' scenario, when multiple persons are talking simultaneously (such as at a family dinner or reception). In such a situation, the hearing device does not know which speaker the user intends to attend to and thus which speaker to enhance and which other ones to suppress. Therefore, a new problem arises in cocktail party problems: determining which speaker a user is attending to, referred to as the auditory attention decoding (AAD) problem. The problem of selecting the attended ...

One of the main complaints of hearing aid users is their degraded speech understanding in noisy environments. Modern hearing aids therefore include noise reduction techniques. These techniques are typically designed for a monaural application, i.e. in a single device. However, the majority of hearing aid users currently have hearing aids at both ears in a so-called bilateral fitting, as it is widely accepted that this leads to a better speech understanding and user satisfaction. Unfortunately, the independent signal processing (in particular the noise reduction) in a bilateral fitting can destroy the so-called binaural cues, namely the interaural time and level differences (ITDs and ILDs) which are used to localize sound sources in the horizontal plane. A recent technological advance are so-called binaural hearing aids, where a wireless link allows for the exchange of data (or even microphone signals) between the ...

A wide range of techniques for coding a single-channel speech and audio signal has been developed over the last few decades. In addition to pure redundancy reduction, sophisticated source and receiver models have been considered for reducing the bit-rate. Traditionally, speech and audio coders are based on different principles and thus each of them offers certain advantages. With the advent of high capacity channels, networks, and storage systems, the bit-rate versus quality compromise will no longer be the major issue; instead, attributes like low-delay, scalability, computational complexity, and error concealments in packet-oriented networks are expected to be the major selling factors. Typical audio coders such as MP3 and AAC are based on subband or transform coding techniques that are not easily reconcilable with a low-delay requirement. The reasons for their inherently longer delay are the relatively long band splitting filters ...

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 ...

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 ...

For humans, the sound is valuable mostly for its meaning. The voice is spoken language, music, artistic intent. Its physiological functioning is highly developed, as well as our understanding of the underlying process. It is a challenge to replicate this analysis using a computer: in many aspects, its capabilities do not match those of human beings when it comes to speech or instruments music recognition from the sound, to name a few. In this thesis, two problems are investigated: the source separation and the musical processing. The first part investigates the source separation using only one Microphone. The problem of sources separation arises when several audio sources are present at the same moment, mixed together and acquired by some sensors (one in our case). In this kind of situation it is natural for a human to separate and to recognize ...

From artificial voices in GPS to automatic systems of dictation, from voice-based identity verification to voice pathology detection, speech processing applications are nowadays omnipresent in our daily life. By offering solutions to companies seeking for efficiency enhancement with simultaneous cost saving, the market of speech technology is forecast to be especially promising in the next years. The present thesis deals with advances in glottal analysis in order to incorporate new techniques within speech processing applications. While current systems are usually based on information related to the vocal tract configuration, the airflow passing through the vocal folds, and called glottal flow, is expected to exhibit a relevant complementarity. Unfortunately, glottal analysis from speech recordings requires specific complex processing operations, which explains why it has been generally avoided. The main goal of this thesis is to provide new advances in glottal analysis ...