Tracking of partials for additive sound synthesis using hidden Markov models

Depalle, Philippe; García, Guillermo; Rodet, Xavier

doi:10.1109/icassp.1993.319096

Cited by 48 publications

(29 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The f p tracks are estimated independently one from the other. A similar model can be seen in [10], where the authors propose a partial tracking strategy that favors the continuity of the slope of the tracks, rather than the continuity in frequency. It is also reported to work well on formant tracking.…”

Section: A Related Workmentioning

confidence: 89%

See 1 more Smart Citation

Source/Filter Factorial Hidden Markov Model, With Application to Pitch and Formant Tracking

Durrieu

Thiran

2013

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Tracking vocal tract formant frequencies (f p ) and estimating the fundamental frequency (f 0 ) are two tracking problems that have been tackled in many speech processing works, often independently, with applications to articulatory parameters estimations, speech analysis/synthesis or linguistics. Many works assume an auto-regressive (AR) model to fit the spectral envelope, hence indirectly estimating the formant tracks from the AR parameters. However, directly estimating the formant frequencies, or equivalently the poles of the AR filter, allows to further model the smoothness of the desired tracks. In this paper, we propose a Factorial Hidden Markov Model combined with a vocal source/filter model, with parameters naturally encoding the f 0 and f p tracks. Two algorithms are proposed, with two different strategies: first, a simplification of the underlying model, with a parameter estimation based on variational methods, and second, a sparse decomposition of the signal, based on Non-negative Matrix Factorization methodology.The results are comparable to state-of-the-art formant tracking algorithms. With the use of a complete production model, the proposed systems provide robust formant tracks which can be used in various applications. The algorithms could also be extended to deal with multiple-speaker signals.

show abstract

Section: A Related Workmentioning

confidence: 89%

“…The variational approximation (VA) proposed in [23] consists in proposing of a joint probability alternative to the "true" probability (10). With that probability proposal, it is easier to compute sufficient statistics or quantities like the posterior probabilities of the FHMM states.…”

Section: A Alternative Joint Probabilitymentioning

confidence: 99%

Source/Filter Factorial Hidden Markov Model, With Application to Pitch and Formant Tracking

Durrieu

Thiran

2013

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…Far from complicating the problem, morphing can be done easily by spectrogram representation as we no longer have to track the sinusoids and their phase [1].…”

Section: Previous Workmentioning

confidence: 99%

“…We will not get an exact copy of 2 d when 1 h = , but some point will be little bit away from their place. The procedure used to find the best 1 t is repeated to find best 2 d for the better results. This can be used to compute the remaining half of the equation for d above.…”

Section: Morphing In Single Dimensionmentioning

confidence: 99%

Automatic Audio Morphing on Detached Sound Waveforms

Kumar¹,

Singh²,

Reddy³

et al. 2012

IJCEE

View full text Add to dashboard Cite

Abstract-This paper describes the techniques to morph between the two portions of sound originated from a common source, broken because of by some reason. We make use of morphing technique to join the sound where the pitch of the sound slowly changes from one broken part to another broken part by slowly changing the pitch information also covering the unvoiced region of the music. Spectral shapes are encoded on the multidimensional space while pitch on orthogonal axes of it. After matching components of the sound, a morph smoothly interpolates the amplitudes to describe a new sound in the same perceptual space. Finally, by inverting the representation, sound is produced. According to the literature survey, this is the first paper which explains the step by step evolution of one sound resulting into other sound across all states of intermediate steps along with the step by step runtime analysis. This will help researchers in future to improve the morphing methodology by looking carefully into the intermediate steps which decides the overall results. Here, we key out representations for morphing, techniques for matching, and interpolation algorithms and morphing each sound component. Spectral images of complete morph spectrogram are shown in the end.

show abstract

“…Several methods are based on McAulay & Quatieri one [2] which is simple and efficient but designed for peak tracking only. In [6], the peak tracking algorithm is based on a hidden Markov models and thus has a high computation complexity. Meanwhile, others methods [7,8] are able to track spectral structures…”

Section: Time-frequency Tracking Of Peaks and Structuresmentioning

confidence: 99%

Monitoring Based on Time-Frequency Tracking of Estimated Harmonic Series and Modulation Sidebands

Gerber

Martin

Mailhes

2015

Applied Condition Monitoring

View full text Add to dashboard Cite

Abstract. A condition monitoring system is a key element in a predictive maintenance strategy allowing to reduce the operating costs of the monitored system. However, the system-driven generation of health indicators requires the knowledge of the system kinematics and the configuration of thresholds which may induce lots of false alarms. In this paper, we propose a generic and data-driven method to automatically generate system health indicators without any a priori knowledge on the monitored system or the acquired signals. The proposed method is based on the automatic detection of spectral content characterising every acquired signal. Within these successive spectral contents, peaks, harmonics series and modulation sidebands are then tracked over time and grouped in time trajectories which will be used to generate the system health indicators.

show abstract

Tracking of partials for additive sound synthesis using hidden Markov models

Cited by 48 publications

References 4 publications

Source/Filter Factorial Hidden Markov Model, With Application to Pitch and Formant Tracking

Source/Filter Factorial Hidden Markov Model, With Application to Pitch and Formant Tracking

Automatic Audio Morphing on Detached Sound Waveforms

Monitoring Based on Time-Frequency Tracking of Estimated Harmonic Series and Modulation Sidebands

Contact Info

Product

Resources

About