D. Cazau

D. Cazau

In the Big Data era, the community of PAM faces strong challenges, including the need for more standardized processing tools accross its different applications in oceanography, and for more scalable and high-performance computing systems to process more efficiently the everly growing datasets. In this work we address conjointly both issues by first proposing a detailed theory-plus-code document of a classical analysis workflow to describe the content of PAM data, which hopefully will be reviewed and adopted by a maximum of PAM experts to make it standardized. Second, we transposed this workflow into the Scala language within the Spark/Hadoop frameworks so it can be directly scaled out on several node cluster.

D. Cazau, G. Nuel

Hidden Markov Models (HMMs) are a ubiquitous tool to model time series data, and have been widely used in two main tasks of Automatic Music Transcription (AMT): note segmentation, i.e. identifying the played notes after a multi-pitch estimation, and sequential post-processing, i.e. correcting note segmentation using training data. In this paper, we employ the multi-pitch estimation method called Probabilistic Latent Component Analysis (PLCA), and develop AMT systems by integrating different HMM-based modules in this framework. For note segmentation, we use two different twostate on/o? HMMs, including a higher-order one for duration modeling. For sequential post-processing, we focused on a musicological modeling of polyphonic harmonic transitions, using a first- and second-order HMMs whose states are defined through candidate note mixtures. These different PLCA plus HMM systems have been evaluated comparatively on two different instrument repertoires, namely the piano (using the MAPS database) and the marovany zither. Our results show that the use of HMMs could bring noticeable improvements to transcription results, depending on the instrument repertoire.

D. Cazau, G. Revillon, O. Adam

Automatic Music Transcription (AMT) is one of the oldest and most well-studied problems in the field of music information retrieval. Within this challenging research field, onset detection and instrument recognition take important places in transcription systems, as they respectively help to determine exact onset times of notes and to recognize the corresponding instrument sources. The aim of this study is to explore the usefulness of multiscale scattering operators for these two tasks on plucked string instrument and piano music. After resuming the theoretical background and illustrating the key features of this sound representation method, we evaluate its performances comparatively to other classical sound representations. Using both MIDI-driven datasets with real instrument samples and real musical pieces, scattering is proved to outperform other sound representations for these AMT subtasks, putting forward its richer sound representation and invariance properties.

D. Cazau, G. Revillon, W. Yuancheng et al.

Automatic Music Transcription (AMT) consists in automatically estimating the notes in an audio recording, through three attributes: onset time, duration and pitch. Probabilistic Latent Component Analysis (PLCA) has become very popular for this task. PLCA is a spectrogram factorization method, able to model a magnitude spectrogram as a linear combination of spectral vectors from a dictionary. Such methods use the Expectation-Maximization (EM) algorithm to estimate the parameters of the acoustic model. This algorithm presents well-known inherent defaults (local convergence, initialization dependency), making EM-based systems limited in their applications to AMT, particularly in regards to the mathematical form and number of priors. To overcome such limits, we propose in this paper to employ a different estimation framework based on Particle Filtering (PF), which consists in sampling the posterior distribution over larger parameter ranges. This framework proves to be more robust in parameter estimation, more flexible and unifying in the integration of prior knowledge in the system. Note-level transcription accuracies of 61.8 $\%$ and 59.5 $\%$ were achieved on evaluation sound datasets of two different instrument repertoires, including the classical piano (from MAPS dataset) and the marovany zither, and direct comparisons to previous PLCA-based approaches are provided. Steps for further development are also outlined.