Content processing is a vast and growing field that integrates different approaches borrowed from the signal processing, information retrieval and machine learning disciplines. In this article we deal with a particular type of content processing: the so-called content-based transformations. We will not focus on any particular application but rather try to give an overview of different techniques and conceptual implications. We first describe the transformation process itself, including the main model schemes that are commonly used, which lead to the establishment of the formal basis for a definition of content-based transformations. Then we take a quick look at a general spectral based analysis/synthesis approach to process audio signals and how to extract features that can be used in the content-based transformation context. Using this analysis/synthesis approach we give some examples on how content-based transformations can be applied to modify the basic perceptual axis of a sound and how we can even combine different basic effects in order to perform more meaningful transformations. We finish by going a step further in the abstraction ladder and present transformations that are related to musical (and thus symbolic) properties rather than to those of the sound or the signal itself.

We present a supervised neural network model for polyphonic piano music transcription. The architecture of the proposed model is analogous to speech recognition systems and comprises an acoustic model and a music language model. The acoustic model is a neural network used for estimating the probabilities of pitches in a frame of audio. The language model is a recurrent neural network that models the correlations between pitch combinations over time. The proposed model is general and can be used to transcribe polyphonic music without imposing any constraints on the polyphony. The acoustic and language model predictions are combined using a probabilistic graphical model. Inference over the output variables is performed using the beam search algorithm. We perform two sets of experiments. We investigate various neural network architectures for the acoustic models and also investigate the effect of combining acoustic and music language model predictions using the proposed architecture. We compare performance of the neural network based acoustic models with two popular unsupervised acoustic models. Results show that convolutional neural network acoustic models yields the best performance across all evaluation metrics. We also observe improved performance with the application of the music language models. Finally, we present an efficient variant of beam search that improves performance and reduces runtimes by an order of magnitude, making the model suitable for real-time applications.

We propose the Probabilistic YIN (PYIN) algorithm, a modification of the well-known YIN algorithm for fundamental frequency (F0) estimation. Conventional YIN is a simple yet effective method for frame-wise monophonic F0 estimation and remains one of the most popular methods in this domain. In order to eliminate short-term errors, outputs of frequency estimators are usually post-processed resulting in a smoother pitch track. One shortcoming of YIN is that such post-processing cannot fall back on alternative interpretations of the signal because the method outputs precisely one estimate per frame. To address this problem we modify YIN to output multiple pitch candidates with associated probabilities (PYIN Stage 1). These probabilities arise naturally from a prior distribution on the YIN threshold parameter. We use these probabilities as observations in a hidden Markov model, which is Viterbi-decoded to produce an improved pitch track (PYIN Stage 2). We demonstrate that the combination of Stages 1 and 2 raises recall and precision substantially. The additional computational complexity of PYIN over YIN is low. We make the method freely available online1 as an open source C++ library for Vamp hosts.

This is the unspecified version of the paper.This version of the publication may differ from the final published version. Abstract Automatic music transcription is considered by many to be a key enabling technology in music signal processing. However, the performance of transcription systems is still significantly below that of a human expert, and accuracies reported in recent years seem to have reached a limit, although the field is still very active. In this paper we analyse limitations of current methods and identify promising directions for future research. Current transcription methods use general purpose models which are unable to capture the rich diversity found in music signals. One way to overcome the limited performance of transcription systems is to tailor algorithms to specific use-cases. Semi-automatic approaches are another way of achieving a more reliable transcription. Also, the wealth of musical scores and corresponding audio data now available are a rich potential source of training data, via forced alignment of audio to scores, but large scale utilisation of such data has yet to be attempted. Other promising approaches include the integration of information from multiple algorithms and different musical aspects. Permanent repository link

We report on the tempo induction contest organized during the International Conference on Music Information Retrieval (ISMIR 2004) held at the University Pompeu Fabra in Barcelona, Spain, in October 2004. The goal of this contest was to evaluate some state-of-the-art algorithms in the task of inducing the basic tempo (as a scalar, in beats per minute) from musical audio signals. To our knowledge, this is the first published large scale cross-validation of audio tempo induction algorithms. Participants were invited to submit algorithms to the contest organizer, in one of several allowed formats. No training data was provided. A total of 12 entries (representing the work of seven research teams) were evaluated, 11 of which are reported in this document. Results on the test set of 3199 instances were returned to the participants before they were made public. Anssi Klapuri's algorithm won the contest. This evaluation shows that tempo induction algorithms can reach over 80% accuracy for music with a constant tempo, if we do not insist on finding a specific metrical level. After the competition, the algorithms and results were analyzed in order to discover general lessons for the future development of tempo induction systems. One conclusion is that robust tempo induction entails the processing of frame features rather than that of onset lists. Further, we propose a new "redundant" approach to tempo induction, inspired by knowledge of human perceptual mechanisms, which combines multiple simpler methods using a voting mechanism. Machine emulation of human tempo induction is still an open issue. Many avenues for future work in audio tempo tracking are highlighted, as for instance the definition of the best rhythmic features and the most appropriate periodicity detection method. In order to stimulate further research, the contest results, annotations, evaluation software and part of the data are available at http://ismir2004.ismir.net/ISMIR-Contest.html

No abstract

BeatRoot is an interactive beat tracking and metrical annotation system which has been used for several years in studies of performance timing. This paper describes improvements to the original system and a large-scale evaluation and analysis of the system's performance. The beat tracking algorithm remains largely unchanged: BeatRoot uses a multiple agent architecture which simultaneously considers several different hypotheses concerning the rate and placement of musical beats, resulting in accurate tracking of the beat, quick recovery from errors, and graceful degradation in cases where the beat is only weakly implied by the data. The original time domain onset detection algorithm, which caused problems for beat tracking music without prominent drums, has been replaced with a more robust onset detector based on spectral flux. Other new features include annotation of multiple metrical levels and phrase boundaries, as well as improvements in the user interface. The software has been rewritten entirely in Java, and it runs on all major operating systems. BeatRoot is evaluated on a new test set of 1360 musical excerpts from a wide range of Western musical styles, and the results are compared with other evaluations such as the MIREX 2006 Audio Beat Tracking Evaluation.

This is the unspecified version of the paper.This version of the publication may differ from the final published version. A method for automatic transcription of polyphonic music is proposed in this work that models the temporal evolution of musical tones. The model extends the shift-invariant probabilistic latent component analysis method by supporting the use of spectral templates that correspond to sound states such as attack, sustain, and decay. The order of these templates is controlled using hidden Markov model-based temporal constraints. In addition, the model can exploit multiple templates per pitch and instrument source. The shift-invariant aspect of the model makes it suitable for music signals that exhibit frequency modulations or tuning changes. Pitch-wise hidden Markov models are also utilized in a postprocessing step for note tracking. For training, sound state templates were extracted for various orchestral instruments using isolated note samples. The proposed transcription system was tested on multiple-instrument recordings from various datasets. Experimental results show that the proposed model is superior to a non-temporally constrained model and also outperforms various state-of-the-art transcription systems for the same experiment. Permanent repository link