Download A Generic System for Audio Indexing: Application to Speech/Music Segmentation and Music Genre Recognition In this paper we present a generic system for audio indexing (classification/ segmentation) and apply it to two usual problems: speech/ music segmentation and music genre recognition. We first present some requirements for the design of a generic system. The training part of it is based on a succession of four steps: feature extraction, feature selection, feature space transform and statistical modeling. We then propose several approaches for the indexing part depending of the local/ global characteristics of the indexes to be found. In particular we propose the use of segment-statistical models. The system is then applied to two usual problems. The first one is the speech/ music segmentation of a radio stream. The application is developed in a real industrial framework using real world categories and data. The performances obtained for the pure speech/ music classes problem are good. However when considering also the non-pure categories (mixed, bed) the performances of the system drop. The second problem is the music genre recognition. Since the indexes to be found are global, “segment-statistical models” are used leading to results close to the state of the art.
Download Audio Processor Parameters: Estimating Distributions Instead of Deterministic Values Audio effects and sound synthesizers are widely used processors
in popular music.
Their parameters control the quality of the
output sound. Multiple combinations of parameters can lead to
the same sound.
While recent approaches have been proposed
to estimate these parameters given only the output sound, those
are deterministic, i.e. they only estimate a single solution among
the many possible parameter configurations.
In this work, we
propose to model the parameters as probability distributions instead
of deterministic values. To learn the distributions, we optimize
two objectives: (1) we minimize the reconstruction error between
the ground truth output sound and the one generated using the
estimated parameters, asisit usuallydone, but also(2)we maximize
the parameter diversity, using entropy. We evaluate our approach
through two numerical audio experiments to show its effectiveness.
These results show how our approach effectively outputs multiple
combinations of parameters to match one sound.
Download Combining classifications based on local and global features: application to singer identification In this paper we investigate the problem of singer identification on acapella recordings of isolated notes. Most of studies on singer identification describe the content of signals of singing voice with features related to the timbre (such as MFCC or LPC). These features aim to describe the behavior of frequencies at a given instant of time (local features). In this paper, we propose to describe sung tone with the temporal variations of the fundamental frequency (and its harmonics) of the note. The periodic and continuous variations of the frequency trajectories are analyzed on the whole note and the features obtained reflect expressive and intonative elements of singing such as vibrato, tremolo and portamento. The experiments, conducted on two distinct data-sets (lyric and pop-rock singers), prove that the new set of features capture a part of the singer identity. However, these features are less accurate than timbre-based features. We propose to increase the recognition rate of singer identification by combining information conveyed by local and global description of notes. The proposed method, that shows good results, can be adapted for classification problem involving a large number of classes, or to combine classifications with different levels of performance.
Download Beat-Marker Location using a Probabilistic Framework and Linear Discriminant Analysis This paper deals with the problem of beat-tracking in an audiofile. Considering time-variable tempo and meter estimation as input, we study two beat-tracking approaches. The first one is based on an adaptation of a method used in speech processing for locating the Glottal Closure Instants. The results obtained with this first approach allow us to derive a set of requirements for a robust approach. This second approach is based on a probabilistic framework. In this approach the beat-tracking problem is formulated as an “inverse” Viterbi decoding problem in which we decode times over beat-numbers according to observation and transition probabilities. A beat-template is used to derive the observation probabilities from the signal. For this task, we propose the use of a machine-learning method, the Linear Discriminant Analysis, to estimate the most discriminative beat-template. We finally propose a set of measures to evaluate the performances of a beattracking algorithm and perform a large-scale evaluation of the two approaches on four different test-sets.
Download Local Key estimation Based on Harmonic and Metric Structures In this paper, we present a method for estimating the local keys of an audio signal. We propose to address the problem of local key finding by investigating the possible combination and extension of different previous proposed global key estimation approaches. The specificity of our approach is that we introduce key dependency on the harmonic and the metric structures. In this work, we focus on the relationship between the chord progression and the local key progression in a piece of music. A contribution of our work is that we address the problem of finding a good analysis window length for local key estimation by introducing information related to the metric structure in our model. Key estimation is not performed on empirical-chosen segment length but on segments that are adapted to the analyzed piece and independent from the tempo. We evaluate and analyze our results on a new database composed of classical music pieces.
Download Production Effect: Audio Features for Recording Techniques Description and Decade Prediction In this paper we address the problem of the description of music production techniques from the audio signal. Over the past decades sound engineering techniques have changed drastically. New recording technologies, extensive use of compressors and limiters or new stereo techniques have deeply modified the sound of records. We propose three features to describe these evolutions in music production. They are based on the dynamic range of the signal, energy difference between channels and phase spread between channels. We measure the relevance of these features on a task of automatic classification of Pop/Rock songs into decades. In the context of Music Information Retrieval this kind of description could be very useful to better describe the content of a song or to assess the similarity between songs.
Download GMM supervector for Content Based Music Similarity Timbral modeling is fundamental in content based music similarity systems. It is usually achieved by modeling the short term features by a Gaussian Model (GM) or Gaussian Mixture Models (GMM). In this article we propose to achieve this goal by using the GMM-supervector approach. This method allows to represent complex statistical models by an Euclidean vector. Experiments performed for the music similarity task showed that this model outperform state of the art approches. Moreover, it reduces the similarity search time by a factor of ≈ 100 compared to state of the art GM modeling. Furthermore, we propose a new supervector normalization which makes the GMM-supervector approach more preformant for the music similarity task. The proposed normalization can be applied to other Euclidean models.
Download Automatic Alignment of Audio Occurrences: Application to the Verification and Synchronization of Audio Fingerprinting Annotation We propose here an original method for the automatic alignment of temporally distorted occurrences of audio items. The method is based on a so-called item-restricted fingerprinting process and a segment detection scheme. The high-precision estimation of the temporal distortions allows to compensate these alterations and obtain a perfect synchronization between the original item and the altered occurrence. Among the applications of this process, we focus on the verification and the alignment of audio fingerprinting annotations. Perceptual evaluation confirms the efficiency of the method in detecting wrong annotations, and confirms the high precision of the synchronization on the occurrences.