Bertrand David

Multipitch Estimation of Piano Sounds Using a New Probabilistic Spectral Smoothness Principle

A new method for the estimation of multiple concurrent pitches in piano recordings is presented. It addresses the issue of overlapping overtones by modeling the spectral envelope of the overtones of each note with a smooth autoregressive model. For the background noise, a moving-average model is used and the combination of both tends to eliminate harmonic and sub-harmonic erroneous pitch estimations. This leads to a complete generative spectral model for simultaneous piano notes, which also explicitly includes the typical deviation from exact harmonicity in a piano overtone series. The pitch set which maximizes an approximate likelihood is selected from among a restricted number of possible pitch combinations as the one. Tests have been conducted on a large homemade database called MAPS, composed of piano recordings from a real upright piano and from high-quality samples.

Fast approximated power iteration subspace tracking

This paper introduces a fast implementation of the power iteration method for subspace tracking, based on an approximation that is less restrictive than the well-known projection approximation. This algorithm, referred to as the fast approximated power iteration (API) method, guarantees the orthonormality of the subspace weighting matrix at each iteration. Moreover, it outperforms many subspace trackers related to the power iteration method, such as PAST, NIC, NP3, and OPAST, while having the same computational complexity. The API method is designed for both exponential windows and sliding windows. Our numerical simulations show that sliding windows offer a faster tracking response to abrupt signal variations.

Source/Filter Model for Unsupervised Main Melody Extraction From Polyphonic Audio Signals

Extracting the main melody from a polyphonic music recording seems natural even to untrained human listeners. To a certain extent it is related to the concept of source separation, with the human ability of focusing on a specific source in order to extract relevant information. In this paper, we propose a new approach for the estimation and extraction of the main melody (and in particular the leading vocal part) from polyphonic audio signals. To that aim, we propose a new signal model where the leading vocal part is explicitly represented by a specific source/filter model. The proposed representation is investigated in the framework of two statistical models: a Gaussian Scaled Mixture Model (GSMM) and an extended Instantaneous Mixture Model (IMM). For both models, the estimation of the different parameters is done within a maximum-likelihood framework adapted from single-channel source separation techniques. The desired sequence of fundamental frequencies is then inferred from the estimated parameters. The results obtained in a recent evaluation campaign (MIREX08) show that the proposed approaches are very promising and reach state-of-the-art performances on all test sets.

Instrument recognition in polyphonic music based on automatic taxonomies

We propose a new approach to instrument recognition in the context of real music orchestrations ranging from solos to quartets. The strength of our approach is that it does not require prior musical source separation. Thanks to a hierarchical clustering algorithm exploiting robust probabilistic distances, we obtain a taxonomy of musical ensembles which is used to efficiently classify possible combinations of instruments played simultaneously. Moreover, a wide set of acoustic features is studied including some new proposals. In particular, signal to mask ratios are found to be useful features for audio classification. This study focuses on a single music genre (i.e., jazz) but combines a variety of instruments among which are percussion and singing voice. Using a varied database of sound excerpts from commercial recordings, we show that the segmentation of music with respect to the instruments played can be achieved with an average accuracy of 53%.

A Musically Motivated Mid-Level Representation for Pitch Estimation and Musical Audio Source Separation

When designing an audio processing system, the target tasks often influence the choice of a data representation or transformation. Low-level time-frequency representations such as the short-time Fourier transform (STFT) are popular, because they offer a meaningful insight on sound properties for a low computational cost. Conversely, when higher level semantics, such as pitch, timbre or phoneme, are sought after, representations usually tend to enhance their discriminative characteristics, at the expense of their invertibility. They become so-called mid-level representations. In this paper, a source/filter signal model which provides a mid-level representation is proposed. This representation makes the pitch content of the signal as well as some timbre information available, hence keeping as much information from the raw data as possible. This model is successfully used within a main melody extraction system and a lead instrument/accompaniment separation system. Both frameworks obtained top results at several international evaluation campaigns.

Musical instrument recognition by pairwise classification strategies

Musical instrument recognition is an important aspect of music information retrieval. In this paper, statistical pattern recognition techniques are utilized to tackle the problem in the context of solo musical phrases. Ten instrument classes from different instrument families are considered. A large sound database is collected from excerpts of musical phrases acquired from commercial recordings translating different instrument instances, performers, and recording conditions. More than 150 signal processing features are studied including new descriptors. Two feature selection techniques, inertia ratio maximization with feature space projection and genetic algorithms are considered in a class pairwise manner whereby the most relevant features are fetched for each instrument pair. For the classification task, experimental results are provided using Gaussian mixture models (GMMs) and support vector machines (SVMs). It is shown that higher recognition rates can be reached with pairwise optimized subsets of features in association with SVM classification using a radial basis function kernel

Sliding window adaptive SVD algorithms

The singular value decomposition (SVD) is an important tool for subspace estimation. In adaptive signal processing, we are especially interested in tracking the SVD of a recursively updated data matrix. This paper introduces a new tracking technique that is designed for rectangular sliding window data matrices. This approach, which is derived from the classical bi-orthogonal iteration SVD algorithm, shows excellent performance in the context of frequency estimation. It proves to be very robust to abrupt signal changes, due to the use of a sliding window. Finally, an ultra-fast tracking algorithm with comparable performance is proposed.

Score informed audio source separation using a parametric model of non-negative spectrogram

In this paper we present a new technique for monaural source separation in musical mixtures, which uses the knowledge of the musical score. This information is used to initialize an algorithm which computes a parametric decomposition of the spectrogram based on non-negative matrix factorization (NMF). This algorithm provides time-frequency masks which are used to separate the sources with Wiener filtering.

High-resolution spectral analysis of mixtures of complex exponentials modulated by polynomials

High-resolution methods such as the ESPRIT algorithm are of major interest for estimating discrete spectra, since they overcome the resolution limit of the Fourier transform and provide very accurate estimates of the signal parameters. In signal processing literature, most contributions focus on the estimation of exponentially modulated sinusoids in a noisy signal. This paper introduces a more general class of signals, involving both amplitude and frequency modulations. It shows that this Polynomial Amplitude Complex Exponentials (PACE) model is the most general model tractable by high-resolution methods. A generalized ESPRIT algorithm is developed for estimating the signal parameters, and it is shown that this model can be characterized by means of a geometrical criterion.

Alginate-encapsulated HepG2 Cells in a Fluidized Bed Bioreactor Maintain Function in Human Liver Failure Plasma

Alginate-encapsulated HepG2 cells cultured in microgravity have the potential to serve as the cellular component of a bioartificial liver. This study investigates their performance in normal and liver failure (LF) human plasma over 6-8 h in a fluidized bed bioreactor. After 8 days of microgravity culture, beads containing 1.5 x 10(9) cells were perfused for up to 8 h at 48 mL/min with 300 mL of plasma. After exposure to 90% LF plasma, vital dye staining showed maintained cell viability, while a 7% increase in lactate dehydrogenase activity indicated minimal cell damage. Glucose consumption, lactate production, and a 4.3-fold linear increase in alpha-fetoprotein levels were observed. Detoxificatory function was demonstrated by quantification of bilirubin conjugation, urea synthesis, and Cyp450 1A activity. These data show that in LF plasma, alginate-encapsulated HepG2 cells can maintain viability, and metabolic, synthetic, and detoxificatory activities, indicating that the system can be scaled-up to form the biological component of a bioartificial liver.