Prof-Life-Log: Personal interaction analysis for naturalistic audio streams

Ziaei, Ali; Sangwan, Abhijeet; Hansen, John H. L.

doi:10.1109/icassp.2013.6639176

Cited by 24 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We observe this effect using mobile personal audio recordings from continuous singlesession audio streams collected over an individual's daily life. Prior advancements in this domain include the "ProfLife-Log" longitudinal study at UT-Dallas Ziaei et al, 2012Ziaei et al, , 2013 which explored speech communication in naturalistic daily life.…”

Section: Objectives and Methodsmentioning

confidence: 99%

The Lombard effect observed in speech produced by cochlear implant users in noisy environments: A naturalistic study

Lee

Ali

Ziaei

et al. 2017

The Journal of the Acoustical Society of America

Self Cite

View full text Add to dashboard Cite

The Lombard effect is an involuntary response speakers experience in the presence of noise during voice communication. This phenomenon is known to cause changes in speech production such as an increase in intensity, pitch structure, formant characteristics, etc., for enhanced audibility in noisy environments. Although well studied for normal hearing listeners, the Lombard effect has received little, if any, attention in the field of cochlear implants (CIs). The objective of this study is to analyze speech production of CI users who are postlingually deafened adults with respect to environmental context. A total of six adult CI users were recruited to produce spontaneous speech in various realistic environments. Acoustic-phonetic analysis was then carried out to characterize their speech production in these environments. The Lombard effect was observed in the speech production of all CI users who participated in this study in adverse listening environments. The results indicate that both suprasegmental (e.g., F0, glottal spectral tilt and vocal intensity) and segmental (e.g., F1 for /i/ and /u/) features were altered in such environments. The analysis from this study suggests that modification of speech production of CI users under the Lombard effect may contribute to some degree an intelligible communication in adverse noisy environments.

show abstract

Section: Objectives and Methodsmentioning

confidence: 99%

The Lombard effect observed in speech produced by cochlear implant users in noisy environments: A naturalistic study

Lee

Ali

Ziaei

et al. 2017

The Journal of the Acoustical Society of America

Self Cite

View full text Add to dashboard Cite

show abstract

“…The weighting factor, ω i , in (2) describes the sharing weight of each PDF in the drawn measurement vector, m 6×1 ,

p false(m false| λ false) = true \sum_{i = 1}^{2} ω_{i} g false(m false| μ_{i}, \sum_{i} false),

where ω i elements are the mixture weights, and g ( x|μ i , Σ i ) represents the probability density functions associated with the Gaussian distributions. Each of the two g ( x|μ i , Σ i ) is estimated from D -variate Gaussian distribution with parameters μ i and Σ i ( i = 1, 2) with their respective means and covariance matrices [32], [33]. λ denotes the model parameters set for the mixture of two Gaussian distributions, represented parametrically by,

λ = false{ω_{i}, μ_{i}, \sum_{i} false}; i = 1, 2.

…”

Section: Mafim System Architecturementioning

confidence: 99%

A Dual-Mode Magnetic–Acoustic System for Monitoring Fluid Intake Behavior in Animals

Sargolzaei

Elahi

Sokoloff³

et al. 2017

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

We have developed an unobtrusive magnetic-acoustic fluid intake monitoring (MAFIM) system using a conventional stainless-steel roller-ball nipple to measure licking and drinking behavior in animals. Movements of a small permanent magnetic tracer attached to stainless-steel roller balls that operate as a tongue-actuated valve are sensed by a pair of 3-axial magnetometers, and transformed into a time series indicating the status of the ball (up or down), using a Gaussian mixture model based data driven classifier. The sounds produced by the rise and fall of the roller balls are also recorded and classified to substantiate the magnetic data by an independent modality for a more robust solution. The operation of the magnetic and acoustic sensors is controlled by an embedded system, communicating via USB with a custom-designed user interface, running on a PC. The MAFIM system has been tested in vivo with mini-pigs, accurately measuring various drinking parameters and licking patterns without constraints imposed by current lick monitoring systems, such as nipple access, animal-nipple contact, animal training, and complex parameter settings.

show abstract

“…In [6], a system that automat ically characterizes background environments was proposed and then exploited to drive better keyword recognition perfor mance. This work was extended in [7], where speech recogni tion, speaker diarization and environment recognition systems were combined to build a system that could reveal details of the subject's daily interaction with both people and environ ment. Finally, in [8], a new technique that can count the total number of words spoken in a day for long duration PARs was proposed.…”

Section: Introductionmentioning

confidence: 99%

Prof-Life-Log: Analysis and classification of activities in daily audio streams

Ziaei

Sangwan

Kaushik

et al. 2015

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

A new method to analyze and classify daily activities in per sonal audio recordings (PARs) is presented. The method em ploys speech activity detection (SAD) and speaker diarization systems to provide high level semantic segmentation of the audio file. Subsequently. a number of audio. speech and lex ical features are computed in order to characterize events in daily audio streams. The features are selected to capture the statistical properties of conversations, topics and turn-taking behavior, which creates a classification space that allows us to capture the differences in interactions. The proposed sys tem is evaluated on 9 days of data from Prof-Life-Log cor pus, which contains naturalistic long duration audio record ings (each file is collected continuously and lasts between 8-to-16 hours). Our experimental results show that the pro posed system achieves good classification accuracy on a dif ficult real-world dataset.

show abstract

Prof-Life-Log: Personal interaction analysis for naturalistic audio streams

Cited by 24 publications

References 8 publications

The Lombard effect observed in speech produced by cochlear implant users in noisy environments: A naturalistic study

The Lombard effect observed in speech produced by cochlear implant users in noisy environments: A naturalistic study

A Dual-Mode Magnetic–Acoustic System for Monitoring Fluid Intake Behavior in Animals

Prof-Life-Log: Analysis and classification of activities in daily audio streams

Contact Info

Product

Resources

About