| 1. |
|
|
| 2. |
- Fotedar, G., et al.
(författare)
-
Automatic recognition of social roles using long term role transitions in small group interactions
- 2016
-
Ingår i: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. ; , s. 2065-2069
-
Konferensbidrag (refereegranskat)abstract
- Recognition of social roles in small group interactions is challenging because of the presence of disfluency in speech, frequent overlaps between speakers, short speaker turns and the need for reliable data annotation. In this work, we consider the problem of recognizing four roles, namely Gatekeeper, Protagonist, Neutral, and Supporter in small group interactions in AMI corpus. In general, Gatekeeper and Protagonist roles occur less frequently compared to Neutral, and Supporter. In this work, we exploit role transitions across segments in a meeting by incorporating role transition probabilities and formulating the role recognition as a decoding problem over the sequence of segments in an interaction. Experiments are performed in a five fold cross validation setup using acoustic, lexical and structural features with precision, recall and F-score as the performance metrics. The results reveal that precision averaged across all folds and different feature combinations improves in the case of Gatekeeper and Protagonist by 13.64% and 12.75% when the role transition information is used which in turn improves the F-score for Gatekeeper by 6.58% while the F-scores for the rest of the roles do not change significantly.
|
|
| 3. |
- Bhowmick, S., et al.
(författare)
-
Arsenic mobilization in the aquifers of three physiographic settings of West Bengal, India : Understanding geogenic and anthropogenic influences
- 2013
-
Ingår i: Journal of Hazardous Materials. - : Elsevier BV. - 0304-3894 .- 1873-3336. ; 262, s. 915-923
-
Tidskriftsartikel (refereegranskat)abstract
- A comparative hydrogeochemical study was carried out in West Bengal, India covering three physiographic regions, Debagram and Chakdaha located in the Bhagirathi-Hooghly alluvial plain and Baruipur in the delta front, to demonstrate the control of geogenic and anthropogenic influences on groundwater arsenic (As) mobilization. Groundwater samples (n=90) from tube wells were analyzed for different physico-chemical parameters. The low redox potential (Eh=-185 to -86mV) and dominant As(III) and Fe(II) concentrations are indicative of anoxic nature of the aquifer. The shallow (<100m) and deeper (>100m) aquifers of Bhagirathi-Hooghly alluvial plains as well as shallow aquifers of delta front are characterized by Ca2+HCO3 - type water, whereas Na+ and Cl- enrichment is found in the deeper aquifer of delta front. The equilibrium of groundwater with respect to carbonate minerals and their precipitation/dissolution seems to be controlling the overall groundwater chemistry. The low SO4 2- and high DOC, PO4 3- and HCO3 - concentrations in groundwater signify ongoing microbial mediated redox processes favoring As mobilization in the aquifer. The As release is influenced by both geogenic (i.e. geomorphology) and anthropogenic (i.e. unsewered sanitation) processes. Multiple geochemical processes, e.g., Fe-oxyhydroxides reduction and carbonate dissolution, are responsible for high As occurrence in groundwaters.
|
|
| 4. |
- Casamitjana, Adrià, et al.
(författare)
-
Bayesian learning for time-varying linear prediction of speech
- 2015
-
Ingår i: 2015 23rd European Signal Processing Conference, EUSIPCO 2015. - : Institute of Electrical and Electronics Engineers (IEEE). - 9780992862633 ; , s. 325-329
-
Konferensbidrag (refereegranskat)abstract
- We develop Bayesian learning algorithms for estimation of time-varying linear prediction (TVLP) coefficients of speech. Estimation of TVLP coefficients is a naturally underdeter-mined problem. We consider sparsity and subspace based approaches for dealing with the corresponding underde-termined system. Bayesian learning algorithms are developed to achieve better estimation performance. Expectation-maximization (EM) framework is employed to develop the Bayesian learning algorithms where we use a combined prior to model a driving noise (glottal signal) that has both sparse and dense statistical properties. The efficiency of the Bayesian learning algorithms is shown for synthetic signals using spectral distortion measure and formant tracking of real speech signals.
|
|
| 5. |
- Chatterjee, D., et al.
(författare)
-
Groundwater arsenic in the fluvial Bengal plains : geochemistry and mitigation
- 2013
-
Ingår i: PROCEEDINGS OF THE FOURTEENTH INTERNATIONAL SYMPOSIUM ON WATER-ROCK INTERACTION, WRI 14. - : ELSEVIER SCIENCE BV. ; , s. 143-146
-
Konferensbidrag (refereegranskat)abstract
- The water quality and chemistry of the groundwater of the fluvial Bengal plains have been investigated. It has been found that shallow aquifers (< 50 m bgl) are contaminated in a few pockets, surrounded by areas with low arsenic (As)/As-free groundwater, while the deeper aquifer (> 100 m bgl) is generally free from As (< 10 mu g/L). It also reveals that multiple As mobilization processes are occurring simultaneously, rather than any single geochemical process. An attempt has been made to demonstrate the degree of As heterogeneity with groundwater quality, and this has been followed by a few local conditions. The study further suggests that the As distribution (spatio-vertical) helps to identify safe shallow aquifers, and several signatures (colour of the sediments /land use pattern/ geomorphological features /local recharge events) are apparent that can be useful for formulating long-term mitigation options.
|
|
| 6. |
- Swamy, P. B., et al.
(författare)
-
Reduced look ahead orthogonal matching pursuit
- 2014
-
Ingår i: 2014 20th National Conference on Communications, NCC 2014. - : IEEE Computer Society. - 9781479923618 ; , s. 6811329-
-
Konferensbidrag (refereegranskat)abstract
- Compressed Sensing (CS) is an elegant technique to acquire signals and reconstruct them efficiently by solving a system of under-determined linear equations. The excitement in this field stems from the fact that we can sample at a rate way below the Nyquist rate and still reconstruct the signal provided some conditions are met. Some of the popular greedy reconstruction algorithms are the Orthogonal Matching Pursuit (OMP), the Subspace Pursuit (SP) and the Look Ahead Orthogonal Matching Pursuit (LAOMP). The LAOMP performs better than the OMP. However, when compared to the SP and the OMP, the computational complexity of LAOMP is higher. We introduce a modified version of the LAOMP termed as Reduced Look Ahead Orthogonal Matching Pursuit (Reduced LAOMP). Reduced LAOMP uses prior information from the results of the OMP and the SP in the quest to speedup the look ahead strategy in the LAOMP. Monte Carlo simulations of this algorithm deliver promising results.
|
|
| 7. |
- Zaki, Ahmed, et al.
(författare)
-
Estimate exchange over network is good for distributed hard thresholding pursuit
- 2019
-
Ingår i: Signal Processing. - : Elsevier. - 0165-1684 .- 1872-7557. ; 156, s. 1-11
-
Tidskriftsartikel (refereegranskat)abstract
- We investigate an existing distributed algorithm for learning sparse signals or data over networks. The algorithm is iterative and exchanges intermediate estimates of a sparse signal over a network. This learning strategy using exchange of intermediate estimates over the network requires a limited communication overhead for information transmission. Our objective in this article is to show that the strategy is good for learning in spite of limited communication. In pursuit of this objective, we first provide a restricted isometry property (RIP)-based theoretical analysis on convergence of the iterative algorithm. Then, using simulations, we show that the algorithm provides competitive performance in learning sparse signals vis-a-vis an existing alternate distributed algorithm. The alternate distributed algorithm exchanges more information including observations and system parameters.
|
|
