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 20 of 36 for “"I-vector"”.

  1. Implementation of i-vector algorithm in speech emotion recognition by using two different classifiers : Gaussian mixture model and support vector machine

    … implementing a comparatively new method, i-vector model. I-vector model has found much success in the areas of speaker identification, speech recognition, and language identification. But it has not been much explored in recognition of emotion. In this research, i-vector model was …

    iupui Repository record for Implementation of i-vector algorithm in speech emotion recognition by using two different classifiers : Gaussian mixture model and support vector machine (opens in a new tab)

  2. Development and Validation of a Remote Sensing Model to Identify Anthropogenic Boreholes that Provide Dry Season, Refuge Habitat for <i>Anopheles</i> Vector Mosquitoes in Sub-Saharan Africa

    … to public health intervention for perennial vector-borne disease transmission in northern tropical savanna region of Kenya. The population in this area are mostly poor nomadic pastoralists with little acquired functional immunity to Plasmodium falciparum, due to infrequent challenges with the …

    usf Repository record for Development and Validation of a Remote Sensing Model to Identify Anthropogenic Boreholes that Provide Dry Season, Refuge Habitat for <i>Anopheles</i> Vector Mosquitoes in Sub-Saharan Africa (opens in a new tab)

  3. Acoustic Approaches to Gender and Accent Identification

    … is concerned with the application of the i-Vector technique to accent identification, which is the most successful approach to acoustic classification to have emerged in recent years. We show that it is possible to achieve high accuracy accent identification without reliance on …

    east-anglia Download PDF for Acoustic Approaches to Gender and Accent Identification (opens in a new tab)

  4. Audio diarization for LENA data and its application to computing language behavior statistics for individuals with autism

    … consisting of infants at risk for autism. I-vector based diarization algorithms were developed for the two datasets to tackle two scenarios: a) some amount of labeled data is present for every speaker present in the audio recording and b) no labeled data is present for the audio recording to …

    gatech Repository record for Audio diarization for LENA data and its application to computing language behavior statistics for individuals with autism (opens in a new tab)

  5. LEARNING UTTERANCE LEVEL REPRESENTATION FROM SPEECH

    … a fixed-length representation (a.k.a. embedding vector), which compactly captures distinctive features over different speakers. There are two popular methods: i-vector and x-vector. Although i-vector is still used, x-vector outperforms i-vector in most SV tasks. However, x-vector has limitations: …

    jhu Repository record for LEARNING UTTERANCE LEVEL REPRESENTATION FROM SPEECH (opens in a new tab)

  6. Applications and Statistical Modeling of Electroencephalograms using Identity Vectors

    … this work introduces the application of Identity Vectors (I-Vectors) to EEG signals. I-Vectors were originally developed in the speech processing community to parse multiple facets of speaker data (speaker, language, accent, age, etc). The similarities between EEG and speech data suggest that …

    temple Repository record for Applications and Statistical Modeling of Electroencephalograms using Identity Vectors (opens in a new tab)

  7. Forensic speaker recognition: speaker and height estimation techniques

    … of the au- thor, is a modification on the i–vector generation process, making it either faster or less memory-demanding, a novel way to perform speaker verification by the use of the Pairwise Support Vector Machine and a new way to perform speaker characteri- sation by means of Deep belief …

    poli-torino Repository record for Forensic speaker recognition: speaker and height estimation techniques (opens in a new tab)

  8. A Long Short-term Memory Neural Network for Improved Twins' Voice Differentiation

    … discussed in comparison to state of the art i-vector methodologies. Results in terms of the equal error rate (EER) indicate that, as the length of the enrollment and test utterances are reduced, the LSTM outperforms the i-vector system by 17% for two seconds of speech data. Of the three speech …

    wvu Repository record for A Long Short-term Memory Neural Network for Improved Twins' Voice Differentiation (opens in a new tab)

  9. Modelling and compensation techniques for short duration speaker verification

    … long. This thesis shows that the conventional i-vector representation, derived from the total variability model, is not an accurate representation for short duration utterances. More accurate models are developed in this thesis. Firstly, a generalization of the total variability model is …

    unsw Repository record for Modelling and compensation techniques for short duration speaker verification (opens in a new tab)

  10. A study of vector and parallel processing

    … This thesis explains the relevance of vector processing and parallel processing, the program candidate selection procedures, and my vector-enabling and parallel-enabling procedures, experiences, and results. This thesis also provides supplemental information about the supercomputing …

    ut-knoxville Repository record for A study of vector and parallel processing (opens in a new tab)

  11. Speaker Verification Systems Under Various Noise and SNR Conditions

    … testing speech length is also examined. The i-vector/Probabilistic Linear Discriminant Analysis method with compensation strategies is shown to provide a stable performance for both previously seen and previously unseen noise scenarios, and a C++ implementation with online processing and …

    ottawa-retro Repository record for Speaker Verification Systems Under Various Noise and SNR Conditions (opens in a new tab)

  12. Speaker Recognition System in Forensic Conditions: The Calibration and Evaluation of the Likelihood Ratio

    … (RUN) and based on the-state-of-the-art i-vector framework. Evaluation of the speaker recognition system was carried out thoroughly by taking into account aspects in both recognition and calibration performances. Duration and noise conditions are two forensic-motivated conditions …

    radboud Repository record for Speaker Recognition System in Forensic Conditions: The Calibration and Evaluation of the Likelihood Ratio (opens in a new tab) Download PDF for Speaker Recognition System in Forensic Conditions: The Calibration and Evaluation of the Likelihood Ratio (opens in a new tab)

  13. Development of an scAAVIGF-I gene therapeutic vector for the enhancement of cartilage repair

    … engineered and used as a gene therapeutic vector to transduce cartilage and synovium and elicit biochemical changes consistent with cartilage repair mechanisms. Here we show joint tissues are permissive to serotype specific, efficient AAV transduction. This is in agreement with previous in …

    colostate Repository record for Development of an scAAVIGF-I gene therapeutic vector for the enhancement of cartilage repair (opens in a new tab)

  14. A study into automatic speaker verification with aspects of deep learning

    … ASV, up to the current state-of-the-art with i-vectors and PLDA. A series of practical tuning experiments then follows. It is found somewhat surprisingly, that even the training of the total variability matrix required for i-vector extraction, is potentially susceptible to unwanted …

    birmingham Download PDF for A study into automatic speaker verification with aspects of deep learning (opens in a new tab)

  15. Towards Automatic Analysis of Audio Recordings from Children with Autism Spectrum Disorder

    … environmental feature representation in the i-vector space can be used to improve the diarization of the audio recordings. Next, we address the issue of diarizing audio recordings of infants and toddlers. We design a fine-tuning mechanism that is applied to a time-delay neural network (TDNN) to …

    gatech Repository record for Towards Automatic Analysis of Audio Recordings from Children with Autism Spectrum Disorder (opens in a new tab)

  16. Children can be Challenging: Automatic Diarization of Child-Guardian Interaction

    … be accounted for. The effective impact on an i-vector or x-vector-based speaker representation is examined. To address age and acoustic environment mismatch, background baby vocalizations are used for augmentation, and their impact is compared to other data augmentation methods. Since both adult …

    jhu Repository record for Children can be Challenging: Automatic Diarization of Child-Guardian Interaction (opens in a new tab)

  17. Automatic assessment of motivational interview with diabetes patients

    … system achieves 43.59% word error rate. The i-vector based diarisation system achieves an F-measure of 0.822. The MITI behaviour code classification system with manual transcriptions achieves an accuracy of 78% for Non Question/Question classification, an accuracy of 80% for Open …

    birmingham Download PDF for Automatic assessment of motivational interview with diabetes patients (opens in a new tab)

  18. Exploring Chondrocyte Integrin Regulation of Growth Factor IGF-I Expression from a Transient pAAV Vector

    … plasmid based adeno-associated virus (pAAV) vector. Because chondrocytes are using cellular machinery to overexpress IGF-I, it is of interest to see whether or not pAAV IGF-I will significantly upregulate or downregulate chondrocyte integrins. Additionally, it is of interest to know whether …

    iupui Repository record for Exploring Chondrocyte Integrin Regulation of Growth Factor IGF-I Expression from a Transient pAAV Vector (opens in a new tab)

  19. Robust gesture recognition

    … via the cubic B-spline interpolation and i-vector method for feature extraction. Finally, remaining issues will be handled by other modeling techniques such as sub-letter stroke modeling. According to experimental results based on the above strategies, the proposed framework clearly improved …

    gatech Repository record for Robust gesture recognition (opens in a new tab)

  20. Intra-speaker Voice Quality Recognition for Voice Therapy

    A critical problem in voice therapy is poor extra-clinical adherence, stemming mainly from patients' difficulty replicating and implementing their prescribed voice technique outside of the therapy session. While clinicians can judge whether a patient's voice quality resembles the individualized …

    gatech Repository record for Intra-speaker Voice Quality Recognition for Voice Therapy (opens in a new tab)

Page 1 of 2