A psychoacoustics based sound onset detection algorithm for polyphonic audio

Thoshkahna, Balaji; Ramakrishnan, K. R.

doi:10.1109/icosp.2008.4697399

Cited by 7 publications

(5 citation statements)

References 9 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To calculate these ERPs, we relied on sound onsets. Importantly, there are many different methods of defining sound onsets (e.g., Thoshkahna and Ramakrishnan, 2008;Böck et al, 2012); for example, some methods are specifically geared for detecting onsets in music (Bello et al, 2005;Haumann et al, 2021). For the online detection of onsets, we optimized the parameters to detect clear, isolated sound onsets in the presence of background noise.…”

Section: Discussionmentioning

confidence: 99%

Real-Time Audio Processing of Real-Life Soundscapes for EEG Analysis: ERPs Based on Natural Sound Onsets

Hölle

Blum

Kissner

et al. 2022

Front. Neuroergonomics

View full text Add to dashboard Cite

With smartphone-based mobile electroencephalography (EEG), we can investigate sound perception beyond the lab. To understand sound perception in the real world, we need to relate naturally occurring sounds to EEG data. For this, EEG and audio information need to be synchronized precisely, only then it is possible to capture fast and transient evoked neural responses and relate them to individual sounds. We have developed Android applications (AFEx and Record-a) that allow for the concurrent acquisition of EEG data and audio features, i.e., sound onsets, average signal power (RMS), and power spectral density (PSD) on smartphone. In this paper, we evaluate these apps by computing event-related potentials (ERPs) evoked by everyday sounds. One participant listened to piano notes (played live by a pianist) and to a home-office soundscape. Timing tests showed a stable lag and a small jitter (< 3 ms) indicating a high temporal precision of the system. We calculated ERPs to sound onsets and observed the typical P1-N1-P2 complex of auditory processing. Furthermore, we show how to relate information on loudness (RMS) and spectra (PSD) to brain activity. In future studies, we can use this system to study sound processing in everyday life.

show abstract

Section: Discussionmentioning

confidence: 99%

Real-Time Audio Processing of Real-Life Soundscapes for EEG Analysis: ERPs Based on Natural Sound Onsets

Hölle

Blum

Kissner

et al. 2022

Front. Neuroergonomics

View full text Add to dashboard Cite

show abstract

“…Importantly, there are many different methods of defining sound onsets (e.g. ; Böck, Krebs, & Schedl, 2012;Thoshkahna & Ramakrishnan, 2008); for example, some methods are specifically geared for detecting onsets in music (Bello et al, 2005;Haumann et al, 2021). For the online detection of onsets, we optimized the parameters to detect clear, isolated sound onsets in the presence of background noise.…”

Section: Discussionmentioning

confidence: 99%

Real-time audio processing of real-life soundscapes for EEG analysis: ERPs based on natural sound onsets

Hölle

Blum

Kissner

et al. 2021

Preprint

View full text Add to dashboard Cite

With smartphone-based mobile electroencephalography (EEG), we can investigate sound perception beyond the lab. To understand sound perception in the real world, we need to relate naturally occurring sounds to EEG data. For this, EEG and audio information need to be synchronized precisely, only then it is possible to capture fast and transient evoked neural responses and relate them to individual sounds. We have developed Android applications (AFEx and Record-a) that allow for the concurrent acquisition of EEG data and audio features, i.e., sound onsets, average signal power (RMS) and power spectral density (PSD) on smartphone. In this paper, we evaluate these apps by computing event-related potentials (ERPs) evoked by everyday sounds. One participant listened to piano notes (played live by a pianist) and to a home-office soundscape. Timing tests showed that the temporal precision of the system is very good. We calculated ERPs to sound onsets and observed the typical P1-N1-P2 complex of auditory processing. Furthermore, we show how to relate information on loudness (RMS) and spectra (PSD) to brain activity. In future studies, we can use this system to study sound processing in everyday life.

show abstract

“…Other more comprehensive studies attempt to improve soft-onset detection using phase information [1,8,9], and combine both energy and phase information to detect any type of onsets [10,11,12,13]. Further studies exploit the multi-resolution analysis [14] getting advantage from the sub-band representation, and apply a psychoacoustics approach [15,16] to mimic the human perception of loudness. Finally, other methods use the linear prediction error obtaining a new onset detection function [17,18,19].…”

Section: Related Workmentioning

confidence: 99%

Multi-resolution linear prediction based features for audio onset detection with bidirectional LSTM neural networks

Marchi

Ferroni

Eyben

et al. 2014

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

View full text Add to dashboard Cite

A plethora of different onset detection methods have been proposed in the recent years. However, few attempts have been made with respect to widely-applicable approaches in order to achieve superior performances over different types of music and with considerable temporal precision. In this paper, we present a multi-resolution approach based on discrete wavelet transform and linear prediction filtering that improves time resolution and performance of onset detection in different musical scenarios. In our approach, wavelet coefficients and forward prediction errors are combined with auditory spectral features and then processed by a bidirectional Long Short-Term Memory recurrent neural network, which acts as reduction function. The network is trained with a large database of onset data covering various genres and onset types. We compare results with state-of-the-art methods on a dataset that includes Bello, Glover and ISMIR 2004 Ballroom sets, and we conclude that our approach significantly outperforms existing methods in terms of F -Measure. For pitched non percussive music an absolute improvement of 7.5% is reported.

show abstract

A psychoacoustics based sound onset detection algorithm for polyphonic audio

Cited by 7 publications

References 9 publications

Real-Time Audio Processing of Real-Life Soundscapes for EEG Analysis: ERPs Based on Natural Sound Onsets

Real-Time Audio Processing of Real-Life Soundscapes for EEG Analysis: ERPs Based on Natural Sound Onsets

Real-time audio processing of real-life soundscapes for EEG analysis: ERPs based on natural sound onsets

Multi-resolution linear prediction based features for audio onset detection with bidirectional LSTM neural networks

Contact Info

Product

Resources

About