@inproceedings{10765, author = {{H.W. Leong, Philip and Amano, Hideharu and Anderson, Jason and Bertels, Koen and M.P. Cardoso, Jo\~ao and Diessel, Oliver and Gogniat, Guy and Hutton, Mike and Lee, JunKyu and Luk, Wayne and Lysaght, Patrick and Platzner, Marco and K. Prasanna, Viktor and Rissa, Tero and Silvano, Cristina and So, Hayden and Wang, Yu}}, booktitle = {{Proceedings of the 25th International Conference on Field Programmable Logic and Applications (FPL)}}, pages = {{1--3}}, publisher = {{Imperial College}}, title = {{{Significant papers from the first 25 years of the FPL conference}}}, doi = {{10.1109/FPL.2015.7293747}}, year = {{2015}}, } @inproceedings{10767, author = {{Ghribi, Ines and Ben Abdallah, Riadh and Khalgui, Mohamed and Platzner, Marco}}, booktitle = {{Proceedings of the 29th European Simulation and Modelling Conference (ESM)}}, title = {{{New Codesign Solutions for Modelling and Partitioning of Probabilistic Reconfigurable Embedded Software}}}, year = {{2015}}, } @article{10770, author = {{Ghasemzadeh Mohammadi, Hassan and Gaillardon, Pierre-Emmanuel and De Micheli, Giovanni}}, journal = {{IEEE Transactions on Nanotechnology}}, number = {{6}}, pages = {{1117--1126}}, publisher = {{IEEE}}, title = {{{From Defect Analysis to Gate-Level Fault Modeling of Controllable-Polarity Silicon Nanowires}}}, doi = {{10.1109/TNANO.2015.2482359}}, volume = {{14}}, year = {{2015}}, } @inproceedings{10771, author = {{Ghasemzadeh Mohammadi, Hassan and Gaillardon, Pierre-Emmanuel and Zhang, Jian and De Micheli, Giovanni and Sanchez, Eduardo and Reorda, Matteo Sonza}}, booktitle = {{2015 IEEE Computer Society Annual Symposium on VLSI}}, pages = {{491--496}}, publisher = {{IEEE}}, title = {{{On the design of a fault tolerant ripple-carry adder with controllable-polarity transistors}}}, doi = {{10.1109/ISVLSI.2015.13}}, year = {{2015}}, } @inproceedings{10772, author = {{Ghasemzadeh Mohammadi, Hassan and Gaillardon, Pierre-Emmanuel and De Micheli, Giovanni}}, booktitle = {{Proceedings of the 2015 Design, Automation & Test in Europe Conference \& Exhibition}}, pages = {{453--458}}, publisher = {{EDA Consortium}}, title = {{{Fault modeling in controllable polarity silicon nanowire circuits}}}, doi = {{10.7873/DATE.2015.0428}}, year = {{2015}}, } @inproceedings{10779, author = {{Guettatfi, Zakarya and Kermia, Omar and Khouas, Abdelhakim}}, booktitle = {{25th International Conference on Field Programmable Logic and Applications (FPL)}}, issn = {{1946-147X}}, keywords = {{embedded systems, field programmable gate arrays, operating systems (computers), scheduling, μC/OS-II, FPGAs, OS foundation, SafeRTOS, Xenomai, chip utilization ration, complex time constraints, embedded systems, hard real-time hardware task allocation, hard real-time hardware task scheduling, hardware-software real-time operating systems, partially reconfigurable field-programmable gate arrays, resource constraints, safety-critical RTOS, Field programmable gate arrays, Hardware, Job shop scheduling, Real-time systems, Shape, Software}}, publisher = {{Imperial College}}, title = {{{Over effective hard real-time hardware tasks scheduling and allocation}}}, doi = {{10.1109/FPL.2015.7293994}}, year = {{2015}}, } @inproceedings{11739, abstract = {{Noise tracking is an important component of speech enhancement algorithms. Of the many noise trackers proposed, Minimum Statistics (MS) is a particularly popular one due to its simple parameterization and at the same time excellent performance. In this paper we propose to further reduce the number of MS parameters by giving an alternative derivation of an optimal smoothing constant. At the same time the noise tracking performance is improved as is demonstrated by experiments employing speech degraded by various noise types and at different SNR values.}}, author = {{Chinaev, Aleksej and Haeb-Umbach, Reinhold}}, booktitle = {{Interspeech 2015}}, keywords = {{speech enhancement, noise tracking, optimal smoothing}}, pages = {{1785--1789}}, title = {{{On Optimal Smoothing in Minimum Statistics Based Noise Tracking}}}, year = {{2015}}, } @inproceedings{11748, abstract = {{We present a semantic analysis technique for spoken input using Markov Logic Networks (MLNs). MLNs combine graphical models with first-order logic. They areparticularly suitable for providing inference in the presence of inconsistent and incomplete data, which are typical of an automatic speech recognizer's (ASR) output in the presence of degraded speech. The target application is a speech interface to a home automation system to be operated by people with speech impairments, where the ASR output is particularly noisy. In order to cater for dysarthric speech with non-canonical phoneme realizations, acoustic representations of the input speech are learned in an unsupervised fashion. While training data transcripts are not required for the acoustic model training, the MLN training requires supervision, however, at a rather loose and abstract level. Results on two databases, one of them for dysarthric speech, show that MLN-based semantic analysis clearly outperforms baseline approaches employing non-negative matrix factorization, multinomial naive Bayes models, or support vector machines.}}, author = {{Despotovic, Vladimir and Walter, Oliver and Haeb-Umbach, Reinhold}}, booktitle = {{INTERSPEECH 2015}}, title = {{{Semantic Analysis of Spoken Input using Markov Logic Networks}}}, year = {{2015}}, } @inproceedings{11755, abstract = {{This contribution presents a Direction of Arrival (DoA) estimation algorithm based on the complex Watson distribution to incorporate both phase and level differences of captured micro- phone array signals. The derived algorithm is reviewed in the context of the Generalized State Coherence Transform (GSCT) on the one hand and a kernel density estimation method on the other hand. A thorough simulative evaluation yields insight into parameter selection and provides details on the performance for both directional and omni-directional microphones. A comparison to the well known Steered Response Power with Phase Transform (SRP-PHAT) algorithm and a state of the art DoA estimator which explicitly accounts for aliasing, shows in particular the advantages of presented algorithm if inter-sensor level differences are indicative of the DoA, as with directional microphones.}}, author = {{Drude, Lukas and Jacob, Florian and Haeb-Umbach, Reinhold}}, booktitle = {{23th European Signal Processing Conference (EUSIPCO 2015)}}, title = {{{DOA-Estimation based on a Complex Watson Kernel Method}}}, year = {{2015}}, } @inproceedings{11810, author = {{Heymann, Jahn and Drude, Lukas and Chinaev, Aleksej and Haeb-Umbach, Reinhold}}, booktitle = {{Automatic Speech Recognition and Understanding Workshop (ASRU 2015)}}, title = {{{BLSTM supported GEV Beamformer Front-End for the 3RD CHiME Challenge}}}, year = {{2015}}, } @inproceedings{11813, abstract = {{The parametric Bayesian Feature Enhancement (BFE) and a datadriven Denoising Autoencoder (DA) both bring performance gains in severe single-channel speech recognition conditions. The first can be adjusted to different conditions by an appropriate parameter setting, while the latter needs to be trained on conditions similar to the ones expected at decoding time, making it vulnerable to a mismatch between training and test conditions. We use a DNN backend and study reverberant ASR under three types of mismatch conditions: different room reverberation times, different speaker to microphone distances and the difference between artificially reverberated data and the recordings in a reverberant environment. We show that for these mismatch conditions BFE can provide the targets for a DA. This unsupervised adaptation provides a performance gain over the direct use of BFE and even enables to compensate for the mismatch of real and simulated reverberant data.}}, author = {{Heymann, Jahn and Haeb-Umbach, Reinhold and Golik, P. and Schlueter, R.}}, booktitle = {{Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on}}, keywords = {{codecs, signal denoising, speech recognition, Bayesian feature enhancement, denoising autoencoder, reverberant ASR, single-channel speech recognition, speaker to microphone distances, unsupervised adaptation, Adaptation models, Noise reduction, Reverberation, Speech, Speech recognition, Training, deep neuronal networks, denoising autoencoder, feature enhancement, robust speech recognition}}, pages = {{5053--5057}}, title = {{{Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions}}}, doi = {{10.1109/ICASSP.2015.7178933}}, year = {{2015}}, } @article{11830, abstract = {{Joint audio-visual speaker tracking requires that the locations of microphones and cameras are known and that they are given in a common coordinate system. Sensor self-localization algorithms, however, are usually separately developed for either the acoustic or the visual modality and return their positions in a modality specific coordinate system, often with an unknown rotation, scaling and translation between the two. In this paper we propose two techniques to determine the positions of acoustic sensors in a common coordinate system, based on audio-visual correlates, i.e., events that are localized by both, microphones and cameras separately. The first approach maps the output of an acoustic self-calibration algorithm by estimating rotation, scale and translation to the visual coordinate system, while the second solves a joint system of equations with acoustic and visual directions of arrival as input. The evaluation of the two strategies reveals that joint calibration outperforms the mapping approach and achieves an overall calibration error of 0.20m even in reverberant environments.}}, author = {{Jacob, Florian and Haeb-Umbach, Reinhold}}, journal = {{ArXiv e-prints}}, title = {{{Absolute Geometry Calibration of Distributed Microphone Arrays in an Audio-Visual Sensor Network}}}, year = {{2015}}, } @book{11868, author = {{Li, Jinyu and Deng, Li and Haeb-Umbach, Reinhold and Gong, Y.}}, publisher = {{Elsevier}}, title = {{{Robust Automatic Speech Recognition}}}, year = {{2015}}, } @inproceedings{11875, abstract = {{Only a few studies exist on automatic emotion analysis of speech from children with Autism Spectrum Conditions (ASC). Out of these, some preliminary studies have recently focused on comparing the relevance of selected prosodic features against large sets of acoustic, spectral, and cepstral features; however, no study so far provided a comparison of performances across different languages. The present contribution aims to fill this white spot in the literature and provide insight by extensive evaluations carried out on three databases of prompted phrases collected in English, Swedish, and Hebrew, inducing nine emotion categories embedded in short-stories. The datasets contain speech of children with ASC and typically developing children under the same conditions. We evaluate automatic diagnosis and recognition of emotions in atypical childrens voice over the nine categories including binary valence/arousal discrimination.}}, author = {{Marchi, Erik and Schuller, Bjoern and Baron-Cohen, Simon and Golan, Ofer and Boelte, Sven and Arora, Prerna and Haeb-Umbach, Reinhold}}, booktitle = {{INTERSPEECH 2015}}, title = {{{Typicality and Emotion in the Voice of Children with Autism Spectrum Condition: Evidence Across Three Languages}}}, year = {{2015}}, } @inproceedings{11919, abstract = {{In this paper we present a source counting algorithm to determine the number of speakers in a speech mixture. In our proposed method, we model the histogram of estimated directions of arrival with a nonparametric Bayesian infinite Gaussian mixture model. As an alternative to classical model selection criteria and to avoid specifying the maximum number of mixture components in advance, a Dirichlet process prior is employed over the mixture components. This allows to automatically determine the optimal number of mixture components that most probably model the observations. We demonstrate by experiments that this model outperforms a parametric approach using a finite Gaussian mixture model with a Dirichlet distribution prior over the mixture weights.}}, author = {{Walter, Oliver and Drude, Lukas and Haeb-Umbach, Reinhold}}, booktitle = {{40th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015)}}, title = {{{Source Counting in Speech Mixtures by Nonparametric Bayesian Estimation of an infinite Gaussian Mixture Model}}}, year = {{2015}}, } @article{11922, abstract = {{Besides the core learning algorithm itself, one major question in machine learning is how to best encode given training data such that the learning technology can efficiently learn based thereon and generalize to novel data. While classical approaches often rely on a hand coded data representation, the topic of autonomous representation or feature learning plays a major role in modern learning architectures. The goal of this contribution is to give an overview about different principles of autonomous feature learning, and to exemplify two principles based on two recent examples: autonomous metric learning for sequences, and autonomous learning of a deep representation for spoken language, respectively.}}, author = {{Walter, Oliver and Haeb-Umbach, Reinhold and Mokbel, Bassam and Paassen, Benjamin and Hammer, Barbara}}, journal = {{KI - Kuenstliche Intelligenz}}, keywords = {{Representation learning, Metric learning, Deep representation, Spoken language}}, pages = {{1--13}}, title = {{{Autonomous Learning of Representations}}}, doi = {{http://dx.doi.org/10.1007/s13218-015-0372-1}}, year = {{2015}}, } @techreport{11923, abstract = {{In this paper we show that recently developed algorithms for unsupervised word segmentation can be a valuable tool for the documentation of endangered languages. We applied an unsupervised word segmentation algorithm based on a nested Pitman-Yor language model to two austronesian languages, Wooi and Waima'a. The algorithm was then modified and parameterized to cater the needs of linguists for high precision of lexical discovery: We obtained a lexicon precision of of 69.2\% and 67.5\% for Wooi and Waima'a, respectively, if single-letter words and words found less than three times were discarded. A comparison with an English word segmentation task showed comparable performance, verifying that the assumptions underlying the Pitman-Yor language model, the universality of Zipf's law and the power of n-gram structures, do also hold for languages as exotic as Wooi and Waima'a.}}, author = {{Walter, Oliver and Haeb-Umbach, Reinhold and Strunk, Jan and P. Himmelmann, Nikolaus }}, title = {{{Lexicon Discovery for Language Preservation using Unsupervised Word Segmentation with Pitman-Yor Language Models (FGNT-2015-01)}}}, year = {{2015}}, } @inproceedings{11969, author = {{Altintas, Onur and Dressler, Falko and Hagenauer, Florian and Matsumoto, Makiko and Sepulcre, Miguel and Sommer, Christoph}}, booktitle = {{2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)}}, isbn = {{9781467371315}}, title = {{{Making cars a main ICT resource in smart cities}}}, doi = {{10.1109/infcomw.2015.7179448}}, year = {{2015}}, } @article{11980, author = {{Bloessl, Bastian and Puschmann, Andre and Sommer, Christoph and Dressler, Falko}}, issn = {{1559-1662}}, journal = {{ACM SIGMOBILE Mobile Computing and Communications Review}}, pages = {{81--90}}, title = {{{Timings Matter}}}, doi = {{10.1145/2721896.2721913}}, year = {{2015}}, } @inproceedings{11981, author = {{Bloessl, Bastian and Sommer, Christoph and Dressler, Falko}}, booktitle = {{2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)}}, isbn = {{9781467371315}}, title = {{{Power matters: Automatic Gain Control for a Software Defined Radio IEEE 802.11a/g/p receiver}}}, doi = {{10.1109/infcomw.2015.7179325}}, year = {{2015}}, }