Acquisition of Communication and Recognition Skills

This page gives access to the public documents produced in and by the project. These documents include the formal deliverables, papers in workshops, conferences and journals, theses and publications targeted at general audiences. 

Del 0.1 Periodic Activity Report [pdf]

Del 1.1 Modules for Conventional Feature Set [pdf]

Del 2.1 Pattern Discovery with Discrete Model Elements [pdf] 

Del 3.1 Memory Architectures [pdf]

Del 4.2 LSA representation and SVD dimension reduction [pdf]

Del 5.1 ACORNS computational model version 2.0 and first experiments [pdf]

[Top of Page]

Del 0.2 Periodic Activity Report on Year 2 [pdf]

Del 1.2  Modules for Feature Augmentation and Selection [pdf]

Del 2.2 Methods for Enhanced Pattern Discovery in Speech Processing [pdf]

Del 3.2 Report focussing on the results of the initial ASR experiments comparing episodic and semantic long term memory [pdf]

Del 4.1 Implementation and test of activation-verification mechanisms [pdf]

Del 5.2 Experiments with basic language learning [pdf]

[Top of Page]

Del 0.2 Periodic Activity Report on Year 3 [pdf]

Del 1.3  Final modules for augmentation of standard spectral features with milli- and centisecond andevaluation on specific phone recognition tasks; Features selected by sensitivity-analysis method [pdf]

Del 2.3 PD module with self-directed search, derived segmental quality measures, full integration of CMM [pdf]

Del 3.3 Report consolidating all results pertaining to memory organisation and access [pdf]

Del 4.3 Final report on exemplar-based and activation based matching [pdf]

Del 5.3 System capable of rapidly learning a large vocabulary [pdf]

Del 6.2 Report on second workshop

Del 6.3 Open Source Software [pdf]

[Top of Page]

Lou Boves, Louis ten Bosch, Roger Moore "ACORNS -- towards computational modeling of communication and recognition skills", Proc. ICCI-2007, [pdf]

Veronique Stouten, Kris Demuynck, Hugo Van hamme "Automatically Learning the Units of Speech by Non-negative Matrix Factorisation",
Proc. Interspeech 2007, [pdf]

Veronique Stouten, Kris Demuynck, Hugo Van hamme "Discovering Phone Patterns in Spoken Utterances by Non-Negative Matrix Factorization", IEEE Signal Processing Letters 2008 [pdf]
The published version of the paper can be accessed through  IEEEXplore <http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=97>
Volume 15,  2008 Page(s):131 - 134, Digital Object Identifier 10.1109/LSP.2007.911723

Louis ten Bosch, Bert Cranen "A computational model for unsupervised word discovery", Proc. Interspeech 2007, [pdf]

Hugo Van hamme "Non-negative Matrix Factorization for Word Acquisition from Multimodal Information Including Speech", ESF Workshop, Leuven November 2007, [pdf]

 [Top of Page]

Hugo Van hamme "Integration of Asynchronous Knowledge Sources in a Novel Speech Recognition Framework", ISCA ITRW, Speech Analysis and Processing for Knowledge Discovery [pdf]

Louis ten Bosch, Hugo Van hamme , Lou Boves "Unsupervised detection of words – questioning the relevance of segmentation", ISCA ITRW, Speech Analysis and Processing for Knowledge Discovery [pdf]

Louis ten Bosch, Lou Boves "Language acquisition: the emergence of words from multimodal input", in Sojka, P., Horák, A., Kopecek, I & Pala, K. (Eds.) Text, Speech and Dialogue, 11th Intern. Conference, TSD 2008, Brno, pp. 261-268 [pdf]

Louis ten Bosch, Hugo Van hamme , Lou Boves "Discovery of words: Towards a computational model of language acquisition", in:  France Mihelič and Janez Žibert (Eds.) Speech Recogition: Technologies and Applications,  Vienna: I-Tech Education and Publishing KG, pp. 205 - 224 [pdf]

Klein, M., Frank, S., van Jaarsveld, H., ten Bosch, L.F.M., & Boves, L. "Unsupervised learning of conceptual representations - a computational neural model", Proc. 14th Annual Conference on Architectures and Mechanisms for Language Processing (AMLaP), 4-6 September 2008, Cambridge, UK [pdf]

Okko Räsänen, Altosaar, T. & Laine U.K. (2008) Comparison of prosodic features in Swedish and Finnish IDS/ADS speech. Proc. of Nordic Prosody X. [pdf]

Okko Räsänen, Unto K. Laine, Toomas Altosaar "Computational language acquisition by statistical bottom-up processing", Proc. Interspeech 2008, pp. 1980-1983 [pdf]

Joris Driesen, Hugo Van hamme "Improving the Multigram Algorithm by using Lattices as Input", Proc. Interspeech 2008, pp. 2086-2089, [pdf]

Hugo Van hamme "HAC-models: a Novel Approach to Continuous Speech Recognition", Proc. Interspeech 2008, pp. 2554-2557, [pdf]

Joost van Doremalen, Lou Boves "Spoken Digit Recognition using a Hierarchical Temporal Memory", Proc. Interspeech 2008, pp. 2566-2569, [pdf]

Louis ten Bosch, Hugo Van hamme, Lou Boves "A computational model of language acquisition: focus on word discovery", Proc. Interspeech 2008, pp. 2570-2573, [pdf] 

[Top of Page]

Louis ten Bosch, Hugo Van hamme , Lou Boves, Roger K. Moore "A computational model of language acquisition: the emergence of words", Fundamenta Informaticae, Vol. 90, (2009), pp. 229-249, [pdf]

Maarten Van Segbroeck and Hugo Van hamme "Unsupervised learning of time-frequency patches as a noise-robust representation of speech", Speech Communication, volume 51, pp. 1124-1138, 2009 [pdf] 

Veronique Stouten and Hugo Van hamme "Automatic voice onset time estimation from reassignment spectra", Speech Communication, Vol. 51, pages 1194-1205, 2009 [pdf]

Michael Klein "Understanding Communicative Intentions Using Simulated Role Reversal", in:  J. Mayor, N. Ruh, & K. Plunkett (Eds.), Connectionist Models of Behaviour and Cognition II. London:World Scientific Publishing, pp 3 - 14, [pdf]

Guillaume Aimetti "Modelling Early Language Acquisition Skills: Towards a General Statistical Learning Mechanism", Proc. EACL-2009, [pdf]

Okko Räsänen & Joris Driesen "A comparison and combination of segmental and fixed-frame signal representations in NMF-based word recognition", Proc. 17th Nordic Conference on Computational Linguistics, 2009 [pdf]

Louis ten Bosch, Joris Driesen, Hugo Van hamme, Lou Boves "On a computational model for language acquisition: modeling cross-speaker generalisation", Proc. Text, Speech and Dialogue, 12th Intern. Conference, TSD 2009 [pdf] 

Guillaume Aimetti, Roger K. Moore, Louis ten Bosch, Okko Räsänen, Unto K. Laine "Discovering Keywords from Cross-Modal Input: Ecological vs. Engineering Methods for Enhancing Acoustic Repetitions", Proc. Interspeech 2009 [pdf]

Roger K. Moore, Louis ten Bosch "Modelling Vocabulary Growth from Birth to Young Adulthood", Proc. Interspeech 2009 [pdf]

Okko J. Räsänen, Unto K. Laine, Toomas Altosaar "A noise robust method for pattern discovery in quantized time series: the concept matrix approach", Proc. Interspeech 2009 [pdf]

Okko J. Räsänen, Unto K. Laine, Toomas Altosaar "An Improved Speech Segmentation Quality Measure: the R-value", Proc. Interspeech 2009 [pdf]

Okko J. Räsänen, Unto K. Laine, Toomas Altosaar "Self-learning Vector Quantization for Pattern Discovery from Speech", Proc. Interspeech 2009 [pdf]

Viktoria Maier, Roger K. Moore "The Case for Case-Based Automatic Speech Recognition", Proc. Interspeech 2009 [pdf]

Saikat Chatterjee, Christos Koniaris and W. Bastiaan Kleijn "Auditory Model Based Optimization of MFCCs Improves Automatic Speech Recognition Performance", Proc. Interspeech 2009 [pdf]

L. ten Bosch, O. Räsänen, J. Driesen, G. Aimetti, T. Altosaar, L. Boves, A. Corns "Do Multiple Caregivers Speed up Language Acquisition?" Proc. Interspeech 2009 [pdf]

Joris Driesen, Louis ten Bosch, Hugo Van hamme "Adaptive Non-negative Matrix Factorization in a Computational Model of Language Acquisition", Proc. Interspeech 2009 [pdf]

Mark Elshaw, Roger K. Moore "A recurrent working memory architecture for emergent speech representation", The Bernstein Conference on Computational Neuroscience (BCCN), 2009, [pdf]

Mark Elshaw, Roger K. Moore and Michael Klein "Hierarchical recurrent self-organising memory (H-RSOM) architecture for an emergent speech representation towards robot grounding", Proc. Conference on Natural Computing and Intelligent Robotics, [pdf]

Louis ten Bosch, Lou Boves and Okko Räsänen "Learning meaningful units from multimodal input – the effect of interaction strategies", Proc. Wocci2009, [pdf]

Guillaume Aimetti, Louis ten Bosch, Roger K. Moore "The emergence of words: Modelling early language acquisition with a dynamic systems perspective", Proc. EpiRob-09,  pp. 17 -- 24. [pdf]

Unto K. Laine, Okko Räsänen “Indirect estimation of formant frequencies through mean spectral variance with application to automatic gender recognition”, Proc. MAVEBA2009, [pdf]

[Top of Page]

Christos Koniaris and Marcin Kuropatwinski and W. Bastiaan Kleijn “Auditory-model based robust feature selection for speech recognition”, J. Acoustical Soc. America Express Letters, [pdf]

Michael Klein, Louis ten Bosch, Lou Boves “Modelling Speech Perception with Restricted Boltzmann Machines:”, Abstracts Neural Computation and Psychology Workshop, Londeon, April 4 – 10, 2010 [pdf]

[Top of Page]

Okko Räsänen "Speech Segmentation and Clustering Methods for a New Speech Recognition Architecture", MSc Thesis, Helsinki University of Technology, Espoo, November 5, 2007, [pdf]

Alexander Bertrand "Zelflerende Spraakherkenning via Matrix-factorisatie", Katholieke Universiteit Leuven - Departement Elektrotechniek ESAT, 2007, [in Dutch]

[Top of Page]

Joost van Doremalen "Hierarchical Temporal Memory Networks for Spoken Digit Recognition", Radboud University Nijmegen, Dept. of Language & Speech, December 2007, [pdf]

Joost De Tollenaere."Zelflerende spraakherkenning: akoestische eenheden en woordmodelllen" MSc thesis, K.U.Leuven, ESAT, 2008, [in Dutch]

[Top of Page]

Article in the Nijmegen University Weekly [in Dutch]

Article in the Nijmegen University Weekly, May 31, 2007, pg. 24 [in Dutch]

[Top of Page]

Article about ACORNS in the IEEE SLTC Newsletter [here]

[Top of Page]

Last updated: 18 November 2011. Please contact Els den Os with any comments, complaints, or reports of broken links.