The paper describes the system built by the team from the University of West Bohemia for participation in the CLEF 2006 CL-SR track. We have decided to concentrate only on the monolingual searching in the Czech test collection and investigate the effect of proper language ...

This paper describes the design of the first large-scale IR test collection built for the Czech language. The creation of this collection also happens to be very challenging, as it is based on a continuous text stream from automatic transcription of spontaneous speech and thus...

Automatic speech recognition, or more precisely language modeling, of the Czech language has to face challenges that are not present in the language modeling of English. Those include mainly the rapid vocabulary growth and closely connected unreliable estimates of the lang...

This paper compares languagemodeling techniques for dialog act segmentation of multiparty meetings. The evaluation is twofold; we search for a convenient representation of textual information and an efficient modeling approach. The textual features capture word identities, parts-of-speech, and...

This paper presents the final version of the Czech Broadcast Conversation Corpus that will shortly be released at the Linguistic Data Consortium (LDC). The corpus contains 72 recordings of a radio discussion program, which yields about 33 hours of transcribed conversational speech from&...

Automatic sentence segmentation of speech is important for enriching speech recognition output and aiding downstream language processing. This paper focuses on automatic sentence segmentation of speech in two different languages -- English and Czech. For this task, we compare and combine thr...

This paper deals with automatic sentence boundary detection in spoken Czech using both textual and prosodic information. This task is important to make automatic speech recognition (ASR) output more readable and easier for downstream language processing modules. We compare and combine three&...

This paper presents a quantitative performance analysis of two different approaches to the lemmatization of the Czech text data. The first one is based on manually prepared dictionary of lemmas and set of derivation rules while the second one is based on automatic inference of...

The research project COMPANIONS aims at developing an advanced embodied conversational agent (ECA). This ECA is used in two scenarios and two languages (English and Czech), and it requires a TTS system being able to generate very natural expressive and emotional speech output. This...

In order to improve speech naturalness of a unit selection TTS system it is necessary to annotate prosodic phrase boundaries in the whole source corpus, which is extremely difficult to achieve manually. It is thus usefull to employ a machine classifier. This paper discusses su...

Objective annotation of prosodic phrases in a corpus for a text-to-speech system is an important issue due to its influence on the naturalness of synthesised speech. The paper discusses drawbacks of common ways of prosodic phrase annotation and proposes a concept of prosodic phrase...

The article discusses differences between a priori and a posteriori phrasing and their importance in the task of automatic prosodic phrasing in text-to-speech systems. On several examples it illustrates shortcomings of common evaluation of a priori phrasing performance using a posteriori phr...

It is natural to dream Artificial Dreams. Are dreams of Artificial Intelligence artificial, or natural? What is the difference between artificial and natural? This difference is given by language and by what can be grasped with words. Good Old-Fashioned AI (GOFAI) cannot create any...

The aim of this article is to analyse in historical context the foundations of contemporary cybernetics and to off er such a defi nition of cybernetics that corresponds both with cybernetics’ original roots as well as its actual institutionalised research ...

The paper discusses a hypothesis relating high quality text-to-speech (TTS) synthesis in spoken dialogue systems with the concept of “uncanny valley”. It introduces a “Wizard-of-Oz” experiment with 30 volunteers engaged in conversations with two synthetic voices of different naturalness. The resu...

This paper describes the method for modifying the baseline speech recognition system to be suitable for a use in spoken dialog system with mixed initiative and natural user’s input. We present three approaches for extending the recognition vocabulary to ensure the spo...

In this paper, we describe an optimized version of a Gaussian-mixture-based acoustic model likelihood evaluation algorithm for graphical processing units (GPUs). The evaluation of these likelihoods is one of the most computationally intensive parts of automatic speech recognizers, but it can ...

An estimation of parameters of a multivariate Gaussian Mixture Model is usually based on a criterion (e.g. Maximum Likelihood) that is focused mostly on training data. Therefore, testing data, which were not seen during the training procedure, may cause problems. Moreover, numerical ins...

Single-Gaussian and Gaussian-Mixture Models are utilized in various pattern recognition tasks. The model parameters are estimated usually via Maximum Likelihood Estimation (MLE) with respect to available training data. However, if only small amount of training data is available, the resulting mod...

The main idea of a priori machine learning is to apply a machine learning method on a machine learning problem itself.We call it "a priori" because the processed data set does not originate from any measurement or other observation.Machine learning which deals with any&#x...