This paper examines the assumption that we continuously while listening tend to focus on the most complex (least repetitive) voice, experiencing this as foreground. We present a computational model calculating the level of attraction a voice in a score is likely to require at a given time. The model is based on a music information complexity measure. Calculating the complexity in each voice ove...

This study presents an effective technique for automatically identifying the singer of a music recording. Since the vast majority of popular music contains background accompaniment during most or all vocal passages, directly acquiring isolated solo voice data for extracting the singer’s vocal characteristics is usually infeasible. To eliminate the interference of background music for singer ide...

Metal subgenres such as, for example, death metal, black doom which are considered as constituents of the »meta-genre« extreme have built up a very specific sound and imagery during last several decades. As Keith Kahn-Harris noticed, this cluster sub-genres gathers musical acts different historical backgrounds ideologies, show highest level diversity, artistic vibrancy dynamics, while at same t...

This paper presents a multi-pitch detection and voice assignment method applied to audio recordings containing a cappella performances with multiple singers. A novel approach combining an acoustic model for multi-pitch detection and a music language model for voice separation and assignment is proposed. The acoustic model is a spectrogram factorization process based on Probabilistic Latent Comp...

An exposure-test paradigm was used to examine whether Dutch listeners can adapt their perception to non-canonical marking of lexical stress in Hungarian-accented Dutch. During exposure, one group of listeners heard only words with correct initial stress, while another group also heard examples of unstressed initial syllables that were marked by high pitch, a possible stress cue in Dutch. Subseq...

Recently, kernel additive modeling with generalized spatial Wiener filtering (GW) was presented for music/voice separation. In this paper, an adaptive auditory filtering, called generalized weighted β-order MMSE estimation (WbE), is applied to the basic iterative kernel back-fitting algorithm for improving the separation performance of monaural music signal into music/voice components. In the p...

This paper describes a novel tool called VIVO (VIsual VOice-leading) that allows to visually define harmonic progressions and voice-leading rules. VIVO comprises of a compiler and a collection of specialized visualization devices. VIVO takes advantage of several music related applications collected under the umbrella of PWGL (PWGL is a free cross-platform visual programming language for music a...

Separating technique for singing voice from music accompaniment is very useful in original sound type Karaoke instrument. We propose a real-time system to separate singing voice from music accompaniment for stereo recordings. Proposed algorithm consists of two stages. The first stage is a spectral change detector. The last stage is a selective vocal separation in frequency bins. Listening tests...