Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 15 of 15 for “"Automatische Spracherkennung"”.

  1. Investigations on discriminative training criteria

    In this work, a framework for efficient discriminative training and modeling is developed and implemented for both small and large vocabulary continuous speech recognition. Special attention will be directed to the comparison and formalization of varying discriminative training criteria and …

    aachen Repository record for Investigations on discriminative training criteria (opens in a new tab)

  2. Diskriminative Modellkombination in Spracherkennungssystemen mit großem Wortschatz

    In this work, the theory of Discriminative Model Combination, DMC, is developed and implemented for large vocabulary continuous speech recognition. DMC is based on a discriminative training of the free parameters of distributions belonging to the exponential family. It is independent of the …

    aachen Repository record for Diskriminative Modellkombination in Spracherkennungssystemen mit großem Wortschatz (opens in a new tab)

  3. Statistische Auswahl von Wortabhängigkeiten in der automatischen Spracherkennung

    This PhD thesis studies the overall effect of statistical language modeling on perplexity and word error rate in automatic speech recognition. A trigram language model with a standard smoothing method is extended by complex state-of-the-art language modeling techniques, including: the comparison of …

    aachen Repository record for Statistische Auswahl von Wortabhängigkeiten in der automatischen Spracherkennung (opens in a new tab)

  4. Normalization in the acoustic feature space for improved speech recognition

    In this work, normalization techniques in the acoustic feature space are studied which improve the robustness of automatic speech recognition systems. It is shown that there is a fundamental mismatch between training and test data which causes degraded recognition performance. Adaptation and …

    aachen Repository record for Normalization in the acoustic feature space for improved speech recognition (opens in a new tab)

  5. Quantile based histogram equalization for noise robust speech recognition

    In many practical applications automatic speech recognition systems have to work in adverse acoustic environment conditions. Automatic systems are much more sensitive to the variabilities of the acoustic signal than humans. Whenever noise causes a mismatch between the distribution of the training …

    aachen Repository record for Quantile based histogram equalization for noise robust speech recognition (opens in a new tab)

  6. Investigations on linear transformations for speaker adaptation and normalization

    This thesis deals with linear transformations at various stages of the automatic speech recognition process. In current state-of-the-art speech recognition systems linear transformations are widely used to care for a potential mismatch of the training and testing data and thus enhance the …

    aachen Repository record for Investigations on linear transformations for speaker adaptation and normalization (opens in a new tab)

  7. Combining natural language processing systems to improve machine translation of speech

    Machine translation of spoken language is a challenging task that involves several natural language processing (NLP) software modules. Human speech in one natural language has to be first automatically transcribed by a speech recognition system. Next, the transcription of the spoken utterance can …

    aachen Repository record for Combining natural language processing systems to improve machine translation of speech (opens in a new tab)

  8. Acoustic feature combination for speech recognition

    In this thesis, the use of multiple acoustic features of the speech signal is considered for speech recognition. The goals of this thesis are twofold: on the one hand, new acoustic features are developed, on the other hand, feature combination methods are investigated in order to find an effective …

    aachen Repository record for Acoustic feature combination for speech recognition (opens in a new tab)

  9. Modeling spontaneous speech variability for large vocabulary continuous speech recognition

    In this work a number of novel techniques for improved treatment of spontaneous speech variabilities in large vocabulary automatic speech recognition are developed and evaluated on US English conversational speech and spontaneous medical dictations. Two main aspects of spontaneous speech modeling …

    aachen Repository record for Modeling spontaneous speech variability for large vocabulary continuous speech recognition (opens in a new tab)

  10. Statistical computer-assisted translation

    In recent years, significant improvements have been achieved in statistical machine translation (MT), but still even the best machine translation technology is far from replacing or even competing with human translators. However, an MT system helps to increase the productivity of human translators. …

    aachen Repository record for Statistical computer-assisted translation (opens in a new tab)

  11. Statistical methods in natural language understanding and spoken dialogue systems

    Modern automatic spoken dialogue systems cover a wide range of applications. There are systems for hotel reservations, restaurant guides, systems for travel and timetable information, as well as systems for automatic telephone-banking services. Building the different components of a spoken dialogue …

    aachen Repository record for Statistical methods in natural language understanding and spoken dialogue systems (opens in a new tab)

  12. Discriminative training and acoustic modeling for automatic speech recognition

    Discriminative training has become an important means for estimating model parameters in many statistical pattern recognition tasks. While standard learning methods based on the Maximum Likelihood criterion aim at optimizing model parameters only class individually, discriminative approaches …

    aachen Repository record for Discriminative training and acoustic modeling for automatic speech recognition (opens in a new tab)

  13. A log-linear discriminative modeling framework for speech recognition

    Conventional speech recognition systems are based on Gaussian hidden Markov models (HMMs).Discriminative techniques such as log-linear modeling have been investigated in speech recognition only recently. This thesis establishes a log-linear modeling framework in the context of discriminative …

    aachen Repository record for A log-linear discriminative modeling framework for speech recognition (opens in a new tab)