A Review of Time-Scale Modification of Music Signals

Abstract

Time-scale modification (TSM) is the task of speeding up or slowing down an audio signal's playback speed without changing its pitch. In digital music production, TSM has become an indispensable tool, which is nowadays integrated in a wide range of music production software. Music signals are diverse-they comprise harmonic, percussive, and transient components, among others. Because of this wide range of acoustic and musical characteristics, there is no single TSM method that can cope with all kinds of audio signals equally well. Our main objective is to foster a better understanding of the capabilities and limitations of TSM procedures. To this end, we review fundamental TSM methods, discuss typical challenges, and indicate potential solutions that combine different strategies. In particular, we discuss a fusion approach that involves recent techniques for harmonic-percussive separation along with time-domain and frequency-domain TSM procedures.

Reconhecimento de Emoções em Sinais de Fala Usando Transferência de Aprendizado

“…Para isso, foram alteradas algumas características das amostras deáudio originais, e os resultados dessas modificações foram acrescentadosà base. A primeira modificação foi realizada com o auxílio de um algoritmo de deslocamento de pitch [26], onde cada amostra deáudio teve seu pitch deslocado de 4 semitons. Esta alteração tornou os sons mais agudos.…”

“…Esta alteração tornou os sons mais agudos. Na segunda modificação, com o auxílio de um algoritmo de alargamento do tempo [26], a escala do tempo das amostras deáudio originais foram modificadas com um fator de alargamento igual a 1,5. Porúltimo, criamos novas amostras deáudio, extraindo o silêncio dos arquivos originais [27], utilizando novamente o detector de atividade vocal com um limiar de…”

Audio Time Stretching Using Fuzzy Classification of Spectral Bins

“…Time-scale modification (TSM) refers to an audio processing technique, which changes the duration of a signal without changing the frequencies contained in that signal [1][2][3]. For example, it is possible to reduce the speed of a speech signal so that it sounds as if the person is speaking more slowly, since the fundamental frequency and the spectral envelope are preserved.…”

“…Audio time stretching has numerous applications, such as fast browsing of speech recordings [4], music production [5], foreign language and music learning [6], fitting of a piece of music to a prescribed time slot [7], and slowing down the soundtrack for slow-motion video [8]. Additionally, TSM is often used as a processing step in pitch shifting, which aims at changing the frequencies in the signal without changing its duration [2,3,7,9,10].…”

“…Even with these kind of signals however, the phase vocoder TSM introduces an artifact typically described as "phasiness" to the processed sound [21,22]. Furthermore, transients processed with the standard phase vocoder suffer from a softening of the perceived attack, often referred to as "transient smearing" [2,3,23]. A standard solution for reducing transient smearing is to apply a phase reset or phase locking at detected transient locations of the input signal [23][24][25].…”