155 research outputs found
Noise robust ASR : missing data techniques and beyond
No full textContains fulltext :
85821.pdf (Publisher’s version ) (Open Access)Radboud Universiteit Nijmegen, 22 maart 2011Promotor : Boves, L.W.J. Co-promotor : Cranen, B.VIII, 161 p
Louis ten Bosch, Annika Hmlinen, Bert Cranen, Lou Boves
No full textggested exploring radically new approaches to address the sound-to-symbol representation. A common factor in all these new approaches is the use of sophisticated models to better impose knowledge-based structure on raw speech data. The issue of using phonological and linguistic structure is central in several lines of current research: on the role of fine phonetic details in lexical decoding ([3]), on the relation between (symbolic) context and pronunciation variation ([4]), and on the design of computational models for human speech processing ([5]). In all these research directions, the combination of statistical data-driven techniques with phonetic-phonological structure is crucial for further improvements. In the final paper, we describe research in this new area, based on computational models for articulatory feature representation of speech. By using these features, we obtain a rich redundant representation that is particularly useful to describe possibly asynchronously events,
Interactivity And Multimodality In The Imix Demonstrator
No full textIt is generally acknowledged that many experts and almost all lay persons have difficulty in formulating requests for information in such a manner that conventional off-line Information Extraction systems can find optimal answers
EM Algorithm with Split and Merge in Trajectory Clustering for Automatic Speech Recognition
No full textAbstract. In this paper, we introduce two reformulated versions of the standard EM algorithm, namely Successive Split EM and Split and Merge EM, to relax the problem of initialization dependence in datadriven Speech Trajectory Clustering. These two algorithms allow us to prevent the EM procedure in Trajectory Clustering from ending in a local maximum of the likelihood surface. Thus, the new methods will generate more coherent trajectory clusters. We applied these two methods for developing multiple parallel HMMs for a continuous digit recognition task. We compared the performance obtained with the proposed methods to the recognition performance obtained with knowledge-based contextdependent Head-Body-Tail models. The results showed that both datadriven approaches significantly outperform the knowledge-based approach. In addition, in most cases the model based on Split and Merge EM is better than the model based on Successive Split EM.
On The Independence Of Digits In Connected Digit Strings
No full textOne of the frequently used assumptions in Speaker Verification is that two speech segments (phonemes, subwords, words) are considered to be independent. And therefore, the log-likelihood of a test utterance is just the sum of the log-likelihoods of the speech segments in that utterance. This paper reports about cases in which this observation-independence assumption seems to be violated, namely for those test utterances which call a certain speech model more than once. For example, a pin code which contains a non-unique digit set performs worse in verification than a pin code which consists of four different digits. Results illustrate that violating the independence assumption too much might result in increasing EERs while more information (in form of digits) is added to the test utterance. 1. INTRODUCTION In Speaker Verification (SV) systems using passwords in the form of fixed or prompted digit strings it seems usual to compute the log-likelihood of a claimant being the true speaker..
What's in a word: sounding sarcastic in British English
No full textItem does not contain fulltext20 p
Data for question answering: The case of why
No full textFor research and development of an approach for automatically answering why-questions (why-QA) a data collection was created. The data set was obtained by way of elicitation and comprises a total of 395 why-questions. For each question, the data set includes the source document and one or two user-formulated answers. In addition, for a subset of the questions, user-formulated paraphrases are available. All question-answer pairs have been annotated with information on topic and semantic answer type. The resulting data set is of importance not only for our research, but we expect it to contribute to and stimulate other research in the field of why-QA
- …
