Musical Instrument Identification based on a Short-Time Spectral Analysis
نویسنده
چکیده
In this paper, an implementation of an audio recognition system for personal computers is presented, combining methodologies of digital signal processing, machine perception, and statistical decision models. In particular, attention was given to musical tones, harmonics, and MIDI notes, that build the musical context to identify two musical instruments from their corresponding musical notes. Altogether nine musical instruments from electronic and acoustic devices have been sampled, with an 89% correct performance for single-mode identification and 67% correct performance for double-mode identification. Key-Words: pattern recognition, Bayes decision theory, statistical classifiers, musical analysis, harmonics
منابع مشابه
BAYESIAN APPROACHES TO MUSICAL INSTRUMENT CLASSIFICATION USING TIMBRE SEGMENTATION by
The task of identifying musical instruments in an audio recording is a difficult problem. While there exists a body of literature on single instrument identification, little research has been performed on the more complex, but real-world, situation of more than one instrument present in the signal. This work proposes a Bayesian method for multi-label classification of musical instrument timbre....
متن کاملClassiication of Musical Instrument Sounds Using Neural Networks
This study introduces the classiication of musical instrument sounds by artiicial neural networks (ANN). The time varying spectral contents of sounds are estimated based on Short-time Fourier Transform (STFT) and are applied to ANN structures for classiication. Recognition results obtained from a multilayer perceptron (MLP), time delay neural network (TDNN) and a hybrid self organizing map radi...
متن کاملAn Accurate Timbre Model for Musical Instruments and its Application to Classification
A compact, general and accurate model of the timbral characteristics of musical instruments can be used as a source of a priori knowledge for music content analysis applications such as transcription and instrument classification, as well as for source separation. We develop a timbre model based on the spectral envelope that meets these requirements and relies on additive analysis, Principal Co...
متن کاملMusical Timbre and Emotion: The Identification of Salient Timbral Features in Sustained Musical Instrument Tones Equalized in Attack Time and Spectral Centroid
Timbre and emotion are two of the most important aspects of musical sounds. Both are complex and multidimensional, and strongly interrelated. Previous research has identified many different timbral attributes, and shown that spectral centroid and attack time are the two most important dimensions of timbre. However, a consensus has not emerged about other dimensions. This study will attempt to i...
متن کاملPerceptually Salient Regions of the Modulation Power Spectrum for Musical Instrument Identification
The ability of a listener to recognize sound sources, and in particular musical instruments from the sounds they produce, raises the question of determining the acoustical information used to achieve such a task. It is now well known that the shapes of the temporal and spectral envelopes are crucial to the recognition of a musical instrument. More recently, Modulation Power Spectra (MPS) have b...
متن کامل