Paper Archive

Automatic language identification for singing is a topic that has not received much attention in the past years. Possible application scenarios include searching for musical pieces in a certain language, improvement of similarity search algorithms for music, and improvement of regional music classification and genre classification. It could also serve to mitigate the "glass ceiling" effect. Most existing approaches employ PPRLM processing (Parallel Phone Recognition followed by Language Modeling). We present a new approach for singing language identification. PLP, MFCC, and SDC features are extracted from audio files and then passed through an i-vector extractor. This algorithm reduces the training data for each sample to a single 450-dimensional feature vector. We then train Neural Networks and Support Vector Machines on these feature vectors. Due to the reduced data, the training process is very fast. The results are comparable to the state of the art, reaching accuracies of 83% on a large speech corpus and 78% on acapella singing. In contrast to PPRLM approaches, our algorithm does not require phoneme-wise annotations and is easier to implement.

Download

This paper proposes a real-time capable method for transcribing and separating occurrences of single drum instruments in polyphonic drum recordings. Both the detection and the decomposition are based on Non-Negative Matrix Factorization and can be implemented with very small systemic delay. We propose a simple modification to the update rules that allows to capture timedynamic spectral characteristics of the involved drum sounds. The method can be applied in music production and music education software. Performance results with respect to drum transcription are presented and discussed. The evaluation data-set consisting of annotated drum recordings is published for use in further studies in the field. Index Terms - drum transcription, source separation, nonnegative matrix factorization, spectral processing, audio plug-in, music production, music education

Download

Exponentially damped sinusoids (EDS) model-based analysis of sound signals often requires a precise estimation of initial amplitudes and phases of the components found in the sound, on top of a good estimation of their frequencies and damping. This can be of the utmost importance in many applications such as high-quality re-synthesis or identification of structural properties of sound generators (e.g. a physical coupling of vibrating devices). Therefore, in those specific applications, an accurate estimation of the onset time is required. In this paper we present a two-step onset time estimation procedure designed for that purpose. It consists of a “rough" estimation using an STFT-based method followed by a time-domain method to “refine" the previous results. Tests carried out on synthetic signals show that it is possible to estimate onset times with errors as small as 0.2ms. These tests also confirm that operating first in the frequency domain and then in the time domain allows to reach a better resolution vs. speed compromise than using only one frequency-based or one time-based onset detection method. Finally, experiments on real sounds (plucked strings and actual percussions) illustrate how well this method performs in more realistic situations.

Download

Recently, we have witnessed an increasing use of the sourcefilter model in music analysis, which is achieved by integrating the source filter model into a non-negative matrix factorisation (NMF) framework or statistical models. The combination of the source-filter model and NMF framework reduces the number of free parameters needed and makes the model more flexible to extend. This paper compares four extended source-filter models: the source-filter-decay (SFD) model, the NMF with timefrequency activations (NMF-ARMA) model, the multi-excitation (ME) model and the source-filter model based on β-divergence (SFbeta model). The first two models represent the time-varying spectra by adding a loss filter and a time-varying filter, respectively. The latter two are extended by using multiple excitations and including a scale factor, respectively. The models are tested using sounds of 15 instruments from the RWC Music Database. Performance is evaluated based on the relative reconstruction error. The results show that the NMF-ARMA model outperforms other models, but uses the largest set of parameters.

Download

In this paper, a polyphonic pitch detection approach is presented, which is based on the iterative analysis of the autocorrelation function. The idea of a two-channel front-end with periodicity estimation by using the autocorrelation is inspired by an algorithm from Tolonen and Karjalainen. However, the analysis of the periodicity in the summary autocorrelation function is enhanced with a more advanced iterative peak picking and pruning procedure. The proposed algorithm is compared to other systems in an evaluation with common data sets and yields good results in the range of state of the art systems.

Download

Robust Principal Component Analysis (RPCA) is a technique to decompose signals into sparse and low rank components, and has recently drawn the attention of the MIR field for the problem of separating leading vocals from accompaniment, with appealing results obtained on small excerpts of music. However, the performance of the method drops when processing entire music tracks. We present an adaptive formulation of RPCA that incorporates music content information to guide the decomposition. Experiments on a set of complete music tracks of various genres show that the proposed algorithm is able to better process entire pieces of music that may exhibit large variations in the music content, and compares favorably with the state-of-the-art.

Download