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 12 of 12 for “"Speaker adaptation"”.

  1. Rapid speaker adaptation with speaker clustering

    Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2002.

    mit Repository record for Rapid speaker adaptation with speaker clustering (opens in a new tab)

  2. Learning speech embeddings for speaker adaptation and speech understanding

    … to propose modeling approaches in order to learn speaker embeddings for speaker adaptation or to learn semantic speech embeddings. The second goal is to introduce training objectives that achieve fairness for the ASR and SLU problems. In the case of speaker adaptation, we introduce an auxiliary …

    uiuc Repository record for Learning speech embeddings for speaker adaptation and speech understanding (opens in a new tab)

  3. Training and speaker adaptation in template-based speech recognition.

    cambridge

  4. Evaluation of speaker adaptation algorithms for public access IVR server

    … is concerned with evaluating the suitability of speaker adaptation methods for improving the performance of the modern speech recognition using minimal time

    cape-town Repository record for Evaluation of speaker adaptation algorithms for public access IVR server (opens in a new tab)

  5. Speaker model adaptation in automatic speech recognition.

    … of automatic speech recognition is to achieve speaker independence. It is generally believed that the main difficulty is the inter-speaker variability in which the acoustic characteristics of different speakers are not the same. There are mainly three approaches to overcome this problem; …

    rgu Repository record for Speaker model adaptation in automatic speech recognition. (opens in a new tab)

  6. Adaptation of hybrid deep neural network-hidden Markov model speech recognition system using a sub-space approach

    … recognition (ASR) system can be enhanced by adaptation of the ASR for a particular speaker or a group of speakers. In ASR, training and testing data often do not follow the same statistics; they are often mismatched, which leads to a gap in performance. The difference between training and …

    gatech Repository record for Adaptation of hybrid deep neural network-hidden Markov model speech recognition system using a sub-space approach (opens in a new tab)

  7. Statistical Recursive Estimation Algorithms for Speaker Adaption

    … statistical recursive estimation algorithms for speaker adaptation. In this thesis, a unified framework for recursive maximum likelihood estimation and recursive Bayesian learning is first developed and applied to direct hidden Markov model parameter estimation. Then an online Bayesian learning …

    uiuc Repository record for Statistical Recursive Estimation Algorithms for Speaker Adaption (opens in a new tab)

  8. Computational differences between whispered and non-whispered speech

    … evaluated. Our approach ef- fectively performs speaker-adaptation for whispered speech acoustic models without needing whispered speech from the target speaker. Results show im- provement over the standard speaker-independent models. Our work opens up additional avenues for research, which are …

    uiuc Repository record for Computational differences between whispered and non-whispered speech (opens in a new tab)

  9. Automatic Speech Recognition Using Deep Neural Networks: New Possibilities

    … frequency variations that commonly happen due to speaker and pronunciation differences in speech signals. Moreover, a new CNN structure called limited weight sharing is proposed to better suit special spectral characteristics of speech signals. Our experimental results have shown that the use of a …

    york Repository record for Automatic Speech Recognition Using Deep Neural Networks: New Possibilities (opens in a new tab)

  10. Joint Training Methods for Tandem and Hybrid Speech Recognition Systems using Deep Neural Networks

    … parameterised functions can also be applied to speaker adaptation tasks. At the ASR system level, DNN acoustic model and corresponding speaker dependent (SD) input feature transforms are jointly learned through minimum phone error (MPE) training as an example of hybrid system joint training, …

    cambridge Repository record for Joint Training Methods for Tandem and Hybrid Speech Recognition Systems using Deep Neural Networks (opens in a new tab)

  11. Using articulatory adjustment to compensate for hypernasality - a modeling study based on measures of electromagnetic articulography (EMA)

    … behaviors developed spontaneously by speakers with VPI on individual bases. This study constructed a speaker-adaptive articulatory model on the basis of the framework of Childers’s vocal tract model to simulate articulatory adjustments aiming at compensating for the acoustic outcome …

    uiuc Repository record for Using articulatory adjustment to compensate for hypernasality - a modeling study based on measures of electromagnetic articulography (EMA) (opens in a new tab)