Mikel Gainza

Onset detection using comb filters

A technique for detecting note onsets using FIR comb filters which have different filter delays is presented. The proposed onset detector focuses on the inharmonic characteristics of the onset component and the energy increases of the signal. Both properties are combined by utilizing FIR comb filters on a frame by frame basis in order to obtain an onset detection function, which is suitable for detecting slow onsets. The proposed approach improves upon existing methods in terms of the percentage of correct detections in signals containing slow onsets.

Automating Ornamentation Transcription

A novel technique for detecting single and multi-note ornaments is presented. The system detects audio segments by utilising an onset detector based on comb filters (ODCF), which is capable of detecting very close events. In addition, a novel method to remove spurious onsets due to offset events is introduced. The system utilises musical ornamentation theory to decide whether a sequence of audio segments correspond to an ornamentation musical structure. In order to evaluate the results, a database of signals produced by different players using the three different instruments has been utilised. The results represent a step forward towards fully automating ornamentation transcription.

Automatic musical meter detection

A method that automatically estimates the metrical structure of a piece of music is presented. The approach is based on the generation of a beat similarity matrix, which provides information about the similarity between any two beats of a piece of music. The repetitive structure of most music is exploited by processing the beat similarity matrix in order to identify similar patterns of beats in different parts of a piece. This principle proves to be equally effective for the detection of both duple and triple meters as well as complex meters. The use of beat positions and dynamic programming techniques allows tracking similar musical patterns formed by beats with moderate tempo deviations. The robustness of the presented approach is reflected by the results presented, where 361 songs are used in order to compare the presented approach against the use of the autocorrelation function in existing state of the art meter detection methods.

Tempo Detection Using a Hybrid Multiband Approach

In this paper, a novel tempo detection system is presented, which suggests the use of a hybrid multiband decomposition. The model tracks the periodicities of different signal property changes that manifest within different frequency bands by using the most appropriate onset/transient detectors for each frequency band. In addition, the proposed system applies a novel method to weight tempo candidates. Each contribution is evaluated by comparing the presented system against existing approaches using three different databases that comprises 1638 songs. These databases include the two publicly available database of songs used in the tempo evaluation contest of ISMIR 2004. These songs are used in order to compare the proposed approach against four recent existing approaches and also against the participants of the tempo detection contest of ISMIR 2004. The results show that the presented approach provides an improvement over existing techniques.

Multi pitch estimation by using modified IIR comb filters

A technique for detecting the pitches of a polyphonic signal of presented. The system utilises modified IIR comb filters, which are generated to ensure that n null (stop band notches) exists at multiples of note frequencies, and that a very flat pass band is present in the remain of the spectrum. Thus, the signal spectrum is not distorted after applying the filters 60 the audio signal, which is the case when using FIR comb filters. The presented approach improves upon an existing multi pitch detection model bared on an FIR comb filter framework,

On the use of a dynamic hybrid tempo detection model for beat tracking

In this paper, an approach that estimates the times at which musical beats occur is presented. The system uses a hybrid multi-band decomposition in order to estimate the music tempo. Following this, beat events are tracked by using a dynamic programming approach, which is updated by using short time tempo estimates. The hybrid decomposition is used in order to calculate the tempo by using different onset detection functions in different frequency bands. In addition, a method that estimates which frequency bands provide reliable periodicities is also presented. The accuracy of the model is evaluated by comparing the presented system against existing approaches using a database of 474 songs.

Onset based audio segmentation for the Irish tin whistle

A technique for segmenting tin whistle audio signals according to the position of the note onsets is presented. This method focuses on the characteristics of the tin whistle within Irish traditional music, customising a time-frequency based representation for detecting the instant when a note starts and releases. Musical ornamentation, such as cuts and strikes, are very common in Irish traditional music and are played during the onset stage. Taking advantage of this musical feature, a novel technique for improving the onset time estimation is also presented.

Interactive Music Archive Access System

The goal of the Interactive Music Archive Access System (IMAAS) project was to develop an interactive music archive access system which was capable of allowing an end-user to easily extract rhythmic, melodic and harmonic musical metadata descriptors from audio, and allow the user to interact with the archive contents in a manner not typically allowed in archive access systems. To this end, the IMAAS system incorporates a range of real-time interaction tools which allow the user to modify the retrieved audio in a number of ways including the ability to isolate individual instruments in stereo mixes, pitch and time-scale modification, and beat-synchronous looping. This demo gives an overview of the capabilities of the IMAAS application.

The DiTME Project: interdisciplinary research in music technology

This paper profiles the emergence of a significant body of research in audio engineering within the Faculties of Engineering and Applied Arts at Dublin Institute of Technology. Over a period of five years the group has had significant success in completing a Strand 3 research project entitled Digital Tools for Music Education (DiTME), followed by successful follow-on projects funded through both the European Framework FP6 and Enterprise Ireland Commercialisation research schemes. The group has solved a number of challenging problems in the audio engineering field and has both published widely and patented a novel sound source separation invention.