A Time-Scale Modification Dataset with Subjective Quality Labels

@article{Roberts2020ATM,
  title={A Time-Scale Modification Dataset with Subjective Quality Labels},
  author={Timothy Roberts and Kuldip K. Paliwal},
  journal={The Journal of the Acoustical Society of America},
  year={2020},
  volume={148 1},
  pages={
          201
        }
}
Time Scale Modification (TSM) is a well-researched field; however, no effective objective measure of quality exists. This paper details the creation, subjective evaluation, and analysis of a dataset for use in the development of an objective measure of quality for TSM. Comprised of two parts, the training component contains 88 source files processed using six TSM methods at 10 time scales, while the testing component contains 20 source files processed using three additional methods at four time… 
2 Citations
Deep Learning-Based Single-Ended Objective Quality Measures for Time-Scale Modified Audio
TLDR
Two single-ended objective quality measures for time-scaled audio are proposed that do not require a reference signal to be evaluated, and are used to evaluate TSM algorithms.
An Objective Measure of Quality for Time-Scale Modification of Audio
TLDR
The proposed OMOQ for time-scaled audio is used to evaluate TSM algorithms, finding that Elastique gives the highest objective quality for solo instrument and voice signals, whereas the identity phase-locking phase vocoder gives the lowest objective quality.

References

SHOWING 1-10 OF 33 REFERENCES
Audio Time Stretching Using Fuzzy Classification of Spectral Bins
TLDR
The proposed time stretching method employs the new concept of fuzzy classification of time-frequency points, or bins, in the spectrogram of the signal, which is applicable to the high-quality time stretching of a wide variety of music signals.
Improved phase vocoder time-scale modification of audio
TLDR
This paper examines the problem of phasiness in the context of time-scale modification and provides new insights into its causes, and two extensions to the standard phase vocoder algorithm are introduced, and the resulting sound quality is shown to be significantly improved.
An Improved Measure of Musical Noise Based on Spectral Kurtosis
  • Matteo Torcoli
  • Physics
    2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)
  • 2019
TLDR
The proposed measure is easily computed, requiring only a fraction of the computational cost of the APS, and shown to clearly outperform the baselines in terms of correlation with the results of both listening tests.
Mel-scale sub-band modelling for perceptually improved time-scale modification of speech and audio signals
TLDR
This work proposes application of time-varying sinusoidal modeling for TSM, without any quasi-stationary assumption, which gives improved quality in comparison to waveform synchronous OLA, phase vocoder with identity phase locking, and the recently proposed harmonic-percussive separation (HPS) based TSM methods.
Phase-vocoder: about this phasiness business
  • J. Laroche, M. Dolson
  • Physics
    Proceedings of 1997 Workshop on Applications of Signal Processing to Audio and Acoustics
  • 1997
TLDR
The problem of phasiness in the context of time-scale modification of signals, and two new phase synchronization schemes which are shown to both significantly improve the sound quality, and reduce the computational cost of such modifications are examined.
Stereo Time-Scale Modification Using Sum and Difference Transformation
  • Timothy Roberts, K. Paliwal
  • Computer Science
    2018 12th International Conference on Signal Processing and Communication Systems (ICSPCS)
  • 2018
TLDR
The proposed method and additional variant for maintaining the phase relationship between channels, and retaining the presence in the centre of the stereo signal as a result, produces a high quality stereo output and greatly improves quality over the independent channel processing method.
Time-Scale Modification Using Fuzzy Epoch-Synchronous Overlap-Add (FESOLA)
  • Timothy Roberts, K. Paliwal
  • Computer Science
    2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)
  • 2019
TLDR
The proposed Fuzzy Epoch-Synchronous Overlap-Add method improves on the previous ESOLA method through the use of cross-correlation to align time-smeared epochs before overlap-adding, which reduces distortion and artefacts while the speaker’s fundamental frequency is stable, as well as reducing artefacts during pitch modulation.
RECOMMENDATION ITU-R BS.1387-1 - Method for objective measurements of perceived audio quality
  • Business
  • 2002
The ITU Radiocommunication Assembly, considering a) that conventional objective methods (e.g. for measuring signal-to-noise ratio and distortion) are no longer adequate for measuring the perceived
Improving Time-Scale Modification of Music Signals Using Harmonic-Percussive Separation
TLDR
This paper presents a TSM approach that handles transients implicitly by first separating the signal into a harmonic component as well as a percussive component which typically contains the transients.
...
1
2
3
4
...