Hugo Van hamme

Also published as: Hugo Van hamme


2018

pdf bib
State Gradients for RNN Memory Analysis
Lyan Verwimp | Hugo Van hamme | Vincent Renkens | Patrick Wambacq
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

We present a framework for analyzing what the state in RNNs remembers from its input embeddings. We compute the gradients of the states with respect to the input embeddings and decompose the gradient matrix with Singular Value Decomposition to analyze which directions in the embedding space are best transferred to the hidden state space, characterized by the largest singular values. We apply our approach to LSTM language models and investigate to what extent and for how long certain classes of words are remembered on average for a certain corpus. Additionally, the extent to which a specific property or relationship is remembered by the RNN can be tracked by comparing a vector characterizing that property with the direction(s) in embedding space that are best preserved in hidden state space.

pdf bib
TF-LM: TensorFlow-based Language Modeling Toolkit
Lyan Verwimp | Hugo Van hamme | Patrick Wambacq
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

2017

pdf bib
Character-Word LSTM Language Models
Lyan Verwimp | Joris Pelemans | Hugo Van hamme | Patrick Wambacq
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers

We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model. Character information can reveal structural (dis)similarities between words and can even be used when a word is out-of-vocabulary, thus improving the modeling of infrequent and unknown words. By concatenating word and character embeddings, we achieve up to 2.77% relative improvement on English compared to a baseline model with a similar amount of parameters and 4.57% on Dutch. Moreover, we also outperform baseline word-level models with a larger number of parameters.

2016

pdf bib
SCALE: A Scalable Language Engineering Toolkit
Joris Pelemans | Lyan Verwimp | Kris Demuynck | Hugo Van hamme | Patrick Wambacq
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

In this paper we present SCALE, a new Python toolkit that contains two extensions to n-gram language models. The first extension is a novel technique to model compound words called Semantic Head Mapping (SHM). The second extension, Bag-of-Words Language Modeling (BagLM), bundles popular models such as Latent Semantic Analysis and Continuous Skip-grams. Both extensions scale to large data and allow the integration into first-pass ASR decoding. The toolkit is open source, includes working examples and can be found on http://github.com/jorispelemans/scale.

pdf bib
Improving cross-domain n-gram language modelling with skipgrams
Louis Onrust | Antal van den Bosch | Hugo Van hamme
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2014

pdf bib
Speech Recognition Web Services for Dutch
Joris Pelemans | Kris Demuynck | Hugo Van hamme | Patrick Wambacq
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

In this paper we present 3 applications in the domain of Automatic Speech Recognition for Dutch, all of which are developed using our in-house speech recognition toolkit SPRAAK. The speech-to-text transcriber is a large vocabulary continuous speech recognizer, optimized for Southern Dutch. It is capable to select components and adjust parameters on the fly, based on the observed conditions in the audio and was recently extended with the capability of adding new words to the lexicon. The grapheme-to-phoneme converter generates possible pronunciations for Dutch words, based on lexicon lookup and linguistic rules. The speech-text alignment system takes audio and text as input and constructs a time aligned output where every word receives exact begin and end times. All three of the applications (and others) are freely available, after registration, as a web application on http://www.spraak.org/webservice/ and in addition, can be accessed as a web service in automated tools.

2013

pdf bib
Comparing and combining classifiers for self-taught vocal interfaces
Lize Broekx | Katrien Dreesen | Jort Florent Gemmeke | Hugo Van hamme
Proceedings of the Fourth Workshop on Speech and Language Processing for Assistive Technologies

pdf bib
Automating speech reception threshold measurements using automatic speech recognition
Hanne Deprez | Emre Yilmaz | Stefan Lievens | Hugo Van hamme
Proceedings of the Fourth Workshop on Speech and Language Processing for Assistive Technologies

pdf bib
A Self Learning Vocal Interface for Speech-impaired Users
Bart Ons | Netsanet Tessema | Janneke van de Loo | Jort Gemmeke | Guy De Pauw | Walter Daelemans | Hugo Van hamme
Proceedings of the Fourth Workshop on Speech and Language Processing for Assistive Technologies

pdf bib
Automatic Monitoring of Activities of Daily Living based on Real-life Acoustic Sensor Data: a preliminary study
Lode Vuegen | Bert Van Den Broeck | Peter Karsmakers | Hugo Van hamme | Bart Vanrumste
Proceedings of the Fourth Workshop on Speech and Language Processing for Assistive Technologies

2012

pdf bib
Towards a Self-Learning Assistive Vocal Interface: Vocabulary and Grammar Learning
Janneke van de Loo | Jort F. Gemmeke | Guy De Pauw | Joris Driesen | Hugo Van hamme | Walter Daelemans
Proceedings of the 1st Workshop on Speech and Multimodal Interaction in Assistive Environments

2008

pdf bib
Recording Speech of Children, Non-Natives and Elderly People for HLT Applications: the JASMIN-CGN Corpus.
Catia Cucchiarini | Joris Driesen | Hugo Van hamme | Eric Sanders
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

Within the framework of the Dutch-Flemish programme STEVIN, the JASMIN-CGN (Jongeren, Anderstaligen en Senioren in Mens-machine Interactie’ Corpus Gesproken Nederlands) project was carried out, which was aimed at collecting speech of children, non-natives and elderly people. The JASMIN-CGN project is an extension of the Spoken Dutch Corpus (CGN) along three dimensions. First, by collecting a corpus of contemporary Dutch as spoken by children of different age groups, elderly people and non-natives with different mother tongues, an extension along the age and mother tongue dimensions was achieved. In addition, we collected speech material in a communication setting that was not envisaged in the CGN: human-machine interaction. One third of the data was collected in Flanders and two thirds in the Netherlands. In this paper we report on our experiences in collecting this corpus and we describe some of the important decisions that we made in the attempt to combine efficiency and high quality.

pdf bib
Children’s Oral Reading Corpus (CHOREC): Description and Assessment of Annotator Agreement
Leen Cleuren | Jacques Duchateau | Pol Ghesquière | Hugo Van hamme
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

Within the scope of the SPACE project, the CHildren’s Oral REading Corpus (CHOREC) is developed. This database contains recorded, transcribed and annotated read speech (42 GB or 130 hours) of 400 Dutch speaking elementary school children with or without reading difficulties. Analyses of inter- and intra-annotator agreement are carried out in order to investigate the consistency with which reading errors are detected, orthographic and phonetic transcriptions are made, and reading errors and reading strategies are labeled. Percentage agreement scores and kappa values both show that agreement between annotations, and therefore the quality of the annotations, is high. Taken all double or triple annotations (for 10% resp. 30% of the corpus) together, % agreement varies between 86.4% and 98.6%, whereas kappa varies between 0.72 and 0.97 depending on the annotation tier that is being assessed. School type and reading type seem to account for systematic differences in % agreement, but these differences disappear when kappa values are calculated that correct for chance agreement. To conclude, an analysis of the annotation differences with respect to the ’*s’ label (i.e. a label that is used to annotate undistinguishable spelling behaviour), phoneme labels, reading strategy and error labels is given.

2006

pdf bib
JASMIN-CGN: Extension of the Spoken Dutch Corpus with Speech of Elderly People, Children and Non-natives in the Human-Machine Interaction Modality
Catia Cucchiarini | Hugo Van hamme | Olga van Herwijnen | Felix Smits
Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)

Large speech corpora (LSC) constitute an indispensable resource for conducting research in speech processing and for developing real-life speech applications. In 2004 the Spoken Dutch Corpus (CGN) became available, a corpus of standard Dutch as spoken by adult natives in the Netherlands and Flanders. Owing to budget constraints, CGN does not include speech of children, non-natives, elderly people and recordings of speech produced in human-machine interactions. Since such recordings would be extremely useful for conducting research and for developing HLT applications for these specific groups of speakers of Dutch, a new project, JASMIN-CGN, was started which aims at extending CGN in different ways: by collecting a corpus of contemporary Dutch as spoken by children of different age groups, non-natives with different mother tongues and elderly people in the Netherlands and Flanders and, in addition, by collecting speech material in a communication setting that was not envisaged in CGN: human-machine interaction. We expect that the knowledge gathered from these data can be generalized to developing appropriate systems also for other speaker groups (i.e. adult natives). One third of the data will be collected in Flanders and two thirds in the Netherlands.

2004

pdf bib
Use and Evaluation of Prosodic Annotations in Dutch
Jacques Duchateau | Tim Ceyssens | Hugo Van hamme
Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)

In the development of annotations for a spoken database, an important issue is whether the annotations can be generated automatically with sufficient precision, or whether expensive manual annotations are needed. In this paper, the case of prosodic annotations is discussed, which was investigated on the CGN database (Spoken Dutch Corpus). The main conclusions of this work are as follows. First, it was found that the available amount of manual prosodic annotations is sufficient for the development of our (baseline, decision tree based) prosodic models. In other words, more manual annotations do not improve the models. Second, the developed prosodic models for prominence are insufficiently accurate to produce automatic prominence annotations that are as good as the manual ones. But on the other hand the consistency between manual and automatic break annotations is as high as the inter-transcriber consistency for breaks. So given the current amount of manual break annotations, annotations for the remainder of the CGN database can be generated automatically with the same quality as the manual annotations.

pdf bib
Evaluation and Adaptation of the Celex Dutch Morphological Database
Tom Laureys | Guy De Pauw | Hugo Van hamme | Walter Daelemans | Dirk Van Compernolle
Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)

This paper describes some important modifications to the Celex morphological database in the context of the FLaVoR project. FLaVoR aims to develop a novel modular framework for speech recognition, enabling the integration of complex linguistic knowledge sources, such as a morphological model. Morphology is a fairly unexploited linguistic information source speech recognizers could benefit from. This is especially true for languages which allow for a rich set of morphological operations, such as our target language Dutch. In this paper we focus on the exploitation of the Celex Dutch morphological database as the information source underlying two different morphological analyzers being developed within the project. Although the Celex database provides a valuable source of morphological information for Dutch, many modifications were necessary before it could be practically applied. We identify major problems, discuss the implemented solutions and finally experimentally evaluate the effect of our modifications to the database.

pdf bib
A Comparison of Two Different Approaches to Morphological Analysis of Dutch
Guy De Pauw | Tom Laureys | Walter Daelemans | Hugo Van hamme
Proceedings of the 7th Meeting of the ACL Special Interest Group in Computational Phonology: Current Themes in Computational Phonology and Morphology