Download Signal Characterization in terms of Sinusoidal and Non-Sinusoidal Components This paper addresses the problem of signal characterization in terms of sinusoidal and non-sinusoidal com-ponents. A first measure of sinusoidality is reviewed. Drawbacks of this sinusoidal estimator are investigated and solutions proposed. Estimation of sinusoidality on non-stationary signal is then made on apre-processed signal. A phase derived sinusoidality measure and the use of Re-estimated Spectra are introduced which allow deriving very precise and local characteristics. Finally, this characterization is used in anew synthesis scheme using Additive and PSOLA synthesis.
Download Musical Key Estimation of Audio Signal Based on Hidden Markov Modeling of Chroma Vectors In this paper, we propose a system for the automatic estimation of the key of a music track using hidden Markov models. The front-end of the system performs transient/noise reduction, estimation of the tuning and then represents the track as a succession of chroma vectors over time. The characteristics of the Major and minor modes are learned by training two hidden Markov models on a labeled database. 24 hidden Markov models corresponding to the various keys are then derived from the two trained models. The estimation of the key of a music track is then obtained by computing the likelihood of its chroma sequence given each HMM. The system is evaluated positively using a database of European baroque, classical and romantic music. We compare the results with the ones obtained using a cognitive-based approach. We also compare the chroma-key profiles learned from the database to the cognitive-based ones.
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 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 Template-Based Estimation of Tempo: Using Unsupervised or Supervised Learning to Create Better Spectral Templates In this paper, we study tempo estimation using spectral templates coming from unsupervised or supervised learning given a database annotated into tempo. More precisely, we study the inclusion of these templates in our tempo estimation algorithm of [1]. For this, we consider as periodicity observation a 48-dimensions vector obtained by sampling the value of the amplitude of the DFT at tempo-related frequencies. We name it spectral template. A set of reference spectral templates is then learned in an unsupervised or supervised way from an annotated database. These reference spectral templates combined with all the possible tempo assumptions constitute the hidden states which we decode using a Viterbi algorithm. Experiments are then performed on the “ballroom dancer” test-set which allows concluding on improvement over state-ofthe-art. In particular, we discuss the use of prior tempo probabilities. It should be noted however that these results are only indicative considering that the training and test-set are the same in this preliminary experiment.
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 Vivos Voco: A survey of recent research on voice transformations at IRCAM IRCAM has a long experience in analysis, synthesis and transformation of voice. Natural voice transformations are of great interest for many applications and can be combine with text-to-speech system, leading to a powerful creation tool. We present research conducted at IRCAM on voice transformations for the last few years. Transformations can be achieved in a global way by modifying pitch, spectral envelope, durations etc. While it sacrifices the possibility to attain a specific target voice, the approach allows the production of new voices of a high degree of naturalness with different gender and age, modified vocal quality, or another speech style. These transformations can be applied in realtime using ircamTools TR A X.Transformation can also be done in a more specific way in order to transform a voice towards the voice of a target speaker. Finally, we present some recent research on the transformation of expressivity.
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.