A comparative study of pitch extraction algorithms on a large variety of singing sounds

Babacan, Onur; Drugman, Thomas; d’Alessandro, Nicolas; Henrich, Nathalie; Dutoit, Thierry

doi:10.1109/icassp.2013.6639185

Cited by 71 publications

(44 citation statements)

References 20 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We calculate recall as the proportion of actually voiced frames (according to the ground truth) which the extractor recognises as voiced and tracks with the correct frequency. We follow [10] and accept a frame as correctly tracked if the estimate is within one semitone of the true frequency. to not making a voicing decision, i.e.…”

Section: Quantitative Analysis On Synthetic Datamentioning

confidence: 99%

See 1 more Smart Citation

PYIN: A fundamental frequency estimator using probabilistic threshold distributions

Mauch

Dixon

2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

221

143

View full text Add to dashboard Cite

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.

show abstract

Section: Quantitative Analysis On Synthetic Datamentioning

confidence: 99%

“…1 http://code.soundsoftware.ac.uk/projects/pyin has gained popularity beyond the speech processing community, especially in the analysis of singing [8,9]. Babacan et al [10] provide an overview of the performance of F0 trackers on singing, in which YIN is shown to be state of the art, and particularly good at fine pitch recognition.…”

Section: Introductionmentioning

confidence: 99%

PYIN: A fundamental frequency estimator using probabilistic threshold distributions

Mauch

Dixon

2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

221

143

View full text Add to dashboard Cite

show abstract

“…Because of its importance, various algorithms for pitch detection have been proposed in the literature [25,26,27]. These methods can be categorized into three groups namely: time domain, frequency domain, and hybrid (combination of both).…”

Section: Pitchmentioning

confidence: 99%

“…These methods can be categorized into three groups namely: time domain, frequency domain, and hybrid (combination of both). In [26], the authors conducted another study on 6 modern pitch detector algorithms.…”

Section: Pitchmentioning

confidence: 99%

See 1 more Smart Citation

Temporal contextual descriptors and applications to emotion analysis.

Balti¹

View full text Add to dashboard Cite

The current trends in technology suggest that the next generation of services and devices allows smarter customization and automatic context recognition. Computers learn the behavior of the users and can offer them customized services depending on the context, location, and preferences.One of the most important challenges in human-machine interaction is the proper understanding of human emotions by machines and automated systems. In the recent years, the progress made in machine learning and pattern recognition led to the development of algorithms that are able to learn the detection and identification of human emotions from experience. These algorithms use different modalities such as image, speech, and physiological signals to analyze and learn human emotions. In many settings, the vocal information might be more available than other modalities due to widespread of voice sensors in phones, cars, and computer systems in general.In emotion analysis from speech, an audio utterance is represented by an ordered (in time) sequence of features or a multivariate time series. Typically, the sequence is further mapped into a global descriptor representative of the entire utterance/sequence. This descriptor is used for classification and analysis. In classic approaches, statistics iii are computed over the entire sequence and used as a global descriptor. This often results in the loss of temporal ordering from the original sequence. Emotion is a succession of acoustic events. By discarding the temporal ordering of these events in the mapping, the classic approaches cannot detect acoustic patterns that lead to a certain emotion.In this dissertation, we propose a novel feature mapping framework. The proposed framework maps temporally ordered sequence of acoustic features into data-driven global descriptors that integrate the temporal information from the original sequence.The framework contains three mapping algorithms. These algorithms integrate the temporal information implicitly and explicitly in the descriptor's representation.In the first algorithm, the Temporal Averaging Algorithm, we average the data temporally using leaky integrators to produce a global descriptor that implicitly integrates the temporal information from the original sequence.In order to integrate the discrimination between classes in the mapping, we propose the Temporal Response Averaging Algorithm which combines the temporal averaging step of the previous algorithm and unsupervised learning to produce data driven temporal contextual descriptors.In the third algorithm, we use the topology preserving property of the Self-Organizing Maps and the continuous nature of speech to map a temporal sequence into an ordered trajectory representing the behavior over time of the input utterance on a 2-D map of emotions. The temporal information is integrated explicitly in the descriptor which makes it easier to monitor emotions in long speeches.The proposed mapping framework maps speech data of different length to the same equivalent representation which allevi...

show abstract