Improved Real-Time Monophonic Pitch Tracking with the Extended Complex Kalman Filter

Das, Orchisama; Smith, Julius O.; Chafe, Chris

doi:10.17743/jaes.2019.0053

Cited by 7 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method uses a Kalman filter to predict the future pitch of the speaker. Kalman filters have been used in the past to perform pitch estimation, for example [19], [20], [21]. In contrast, the proposed system only uses the Kalman filter for future pitch prediction and not pitch estimation.…”

Section: Introductionmentioning

confidence: 99%

Speaker Change Detection Using Fundamental Frequency with Application to Multi-talker Segmentation

Hogg

Evers

Naylor

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper shows that time varying pitch properties can be used advantageously within the segmentation step of a multi-talker diarization system. First a study is conducted to verify that changes in pitch are strong indicators of changes in the speaker. It is then highlighted that an individual's pitch is smoothly varying and therefore can be predicted by means of a Kalman filter. Subsequently it is shown that if the pitch is not predictable then this is most likely due to a change in the speaker. Finally, a novel system is proposed that uses this approach of pitch prediction for speaker change detection. This system is then evaluated against a commonly used MFCC segmentation system. The proposed system is shown to increase the speaker change detection rate from 43.3% to 70.5% on meetings in the AMI corpus. Therefore there are two equally weighted contributions in this paper: 1. We address the question of whether a change in pitch is a reliable estimator of a speaker change in multi-talk meeting audio. 2. We develop a method to extract such speaker changes and test them on a widely available meeting corpus.

show abstract

Section: Introductionmentioning

confidence: 99%

Speaker Change Detection Using Fundamental Frequency with Application to Multi-talker Segmentation

Hogg

Evers

Naylor

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Matlab is used to implement Extended Complex Kalman Filter (ECKF) [7] and the PLL-Based pitch detection [6] algorithms.…”

Section: Pitch Detection Algorithmsmentioning

confidence: 99%

“…This obviates the need for explicit tracking following the estimation as it is built in to the algorithm. These use techniques from other areas of signal processing, that is the Phase-locked loop (PLL) [6], a communications tool, and the Extended Kalman filter [7], more familiar in statistical signal detection. These take as input the audio signal and provide a value for the pitch at every sample.…”

Section: Introductionmentioning

confidence: 99%

“…The initial PLL method was augmented to have a set of PLLs to track the pitch and the most likely pitch value selected [6]. The Extended Kalman Filter can produce good results according to [7] but care is required when setting the parameters of the signal model. Another recent work is the Harmonic locking Loop [8], which extends the tracking idea to all harmonics to produce an improved estimate.…”

Section: Introductionmentioning

confidence: 99%

“…It is noteworthy that PLL and Kalman Filter have been evaluated only with one instrument and no a human's voice, PLL with cello [6] and Kalman Filter with guitar [7]. Therefore, this study evaluates their performance for humans' voice…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An investigation into several pitch detection algorithms for singing phrases analysis

Faghih

Timoney

2019

2019 30th Irish Signals and Systems Conference (ISSC)

View full text Add to dashboard Cite

This article provides an investigation into four different pitch detection algorithms: pYin, Praat, Phase Lock Loops (PLL)-based, and an Extended Complex Kalman Filter approach. The first two algorithms compute the pitch on a frame-by-frame basis while the latter two work on a sample-bysample basis. Only in recent years has there been a noticeable increase in the number of papers applying pitch detection techniques to sung phrases. This investigation is done on a dataset contained 76 files of singers. To create a ground truth from the data an alternative approach using the Spear analysis program is applied. The algorithms are compared using a new Singing Data Analyser tool. It was observed that the pYin and Praat are the most reliable algorithms while the PLL and Kalman filter algorithms are very dependent on the userselected parameters.

show abstract

The Period-Modulated Harmonic Locked Loop (PM-HLL): A low-effort algorithm for rapid time-domain multi-periodicity estimation

Hohmann

2021

Acta Acust.

View full text Add to dashboard Cite

Many speech and music analysis and processing schemes rely on an estimate of the fundamental frequency f0 of periodic signal components. Most established schemes apply rather unspecific signal models such as sinusoidal models to the estimation problem, which may limit time resolution and estimation accuracy. This study proposes a novel time-domain locked-loop algorithm with low computational effort and low memory footprint for f0 estimation. The loop control signal is directly derived from the input time signal, using a harmonic signal model. Theoretically, this allows for a noise-robust and rapid f0 estimation for periodic signals of arbitrary waveform, and without the requirement of a prior frequency analysis. Several simulations with short signals employing different types of periodicity and with added wide-band noise were performed to demonstrate and evaluate the basic properties of the proposed algorithm. Depending on the Signal-to-Noise Ratio (SNR), the estimator was found to converge within 3–4 signal repetitions, even at SNR close to or below 0 dB. Furthermore, it was found to follow fundamental frequency sweeps with a delay of less than one period and to track all tones of a three-tone musical chord signal simultaneously. Quasi-periodic sounds with shifted harmonics as well as signals with stochastic periodicity were robustly tracked. Mean and standard deviation of the estimation error, i.e., the difference between true and estimated f0, were at or below 1 Hz in most cases. The results suggest that the proposed algorithm may be applicable to low-delay speech and music analysis and processing.

show abstract

Improved Real-Time Monophonic Pitch Tracking with the Extended Complex Kalman Filter

Cited by 7 publications

References 0 publications

Speaker Change Detection Using Fundamental Frequency with Application to Multi-talker Segmentation

Speaker Change Detection Using Fundamental Frequency with Application to Multi-talker Segmentation

An investigation into several pitch detection algorithms for singing phrases analysis

The Period-Modulated Harmonic Locked Loop (PM-HLL): A low-effort algorithm for rapid time-domain multi-periodicity estimation

Contact Info

Product

Resources

About