Acoustic environment identification using unsupervised learning

Abstract

Acoustic environment leaves its characteristic signature in the audio recording captured in it. The acoustic environment signature can be modeled using acoustic reverberations and background noise. Acoustic reverberation depends on the geometry and composition of the recording location. The proposed scheme uses similarity in the estimated acoustic signature for acoustic environment identification (AEI). We describe a parametric model to realize acoustic reverberation, and a statistical framework based on maximum likelihood estimation is used to estimate the model parameters. The density-based clustering is used for automatic AEI using estimated acoustic parameters. Performance of the proposed framework is evaluated for two data sets consisting of hand-clapping and speech recordings made in a diverse set of acoustic environments using three microphones. Impact of the microphone type variation, frequency, and clustering accuracy and efficiency on the performance of the proposed method is investigated. Performance of the proposed method is also compared with the existing state-of-the-art (SoA) for AEI.

Discriminative feature domains for reverberant acoustic environments

“…1. Room-type identification, for which practical applications involve context recognition and environment identification for data-mining [17,6].…”

Handclap for Acoustic Measurements: Optimal Application and Limitations

“…Early decay time is defined as the time interval required for the sound energy level to decay 10 dB after the excitation has stopped [42], and it is evaluated from the slope of the impulse response-decay curves (as the conventional T). The slope of the decay curve is determined from the slope of the best-fit linear regression line of the initial 10 dB (between 0 dB and −10 dB) of the decay.…”

“…Finally, handclap can also be used for other applications such as clap based electrical appliance control [37,38], speech dereverberation [39][40][41], acoustic environment identification using unsupervised learning [42], and for sonic interactions with a computer [43,44]. Handclap can also be used to form a language as a common means of communication between humans and robots [45], to estimate the performance of acoustic absorbers [46], and as a source for a localization technique using a mobile phone [47].…”

Cell phone verification from speech recordings using sparse representation

“…In a verification test, for a claimed device, select 1 N object examples from claimed device and 2 N non-target background…”

“…Reliable recognition of the source device used to acquire a particular speech recording would prove useful in the court for establishing the origin of speech recordings presented as evidence [1,2]. Source recording device recognition is motivated by the hypothesis that recording device leave behind its intrinsic fingerprint traces in the speech recording [3].…”