Learn More
—We describe an acoustic chord transcription system that uses symbolic data to train hidden Markov models and gives best-of-class frame-level recognition results. We avoid the extremely laborious task of human annotation of chord names and boundaries—which must be done to provide machine learning models with ground truth—by performing automatic harmony(More)
A new approach for acoustic chord transcription and key extraction is presented. We use a novel method of acquiring a large set of labeled training data for automatic key/chord recognition from the raw audio without the enormously laborious process of manual annotation. To this end, we first perform harmonic analysis on symbolic data to extract the key(More)
In this paper, we propose a novel method for obtaining labeled training data to estimate the parameters in a supervised learning model for automatic chord recognition. To this end, we perform harmonic analysis on symbolic data to generate label files. In parallel, we generate audio data from the same symbolic data, which are then provided to a machine(More)
The human ability to recognize, identify and compare sounds based on their approximation of particular vowels provides an intuitive, easily learned representation for complex data. We describe implementations of vocal tract models specifically designed for sonification purposes. The models described are based on classical models including Klatt[1] and(More)
The short-time Fourier transform (STFT) based spectrogram is commonly used to analyze the time-frequency content of a signal. Depending on window size, the STFT provides a trade-off between time and frequency resolutions. This paper presents a novel method that achieves high resolution simultaneously in both time and frequency. We extend Probabilistic(More)