Sökning: "Speech Learning Model"

Visar resultat 1 - 5 av 33 uppsatser innehållade orden Speech Learning Model.

  1. 1. Perception of English /l/ and /r/ by Japanese listeners – the influence of living abroad.

    Kandidat-uppsats, Göteborgs universitet/Institutionen för språk och litteraturer

    Författare :Axel Hooper; [2019-03-05]
    Nyckelord :japanska; perception; phoneme; allophone; Speech Learning Model;

    Sammanfattning : This thesis explores the topic of perception of /l/ and /r/ phonemes in Japanese speakers, primarily divided into two groups: Speakers who have lived in Sweden for 3 or more years and speak conversational Swedish, and average Japanese speakers, in an attempt to observe the effects learning Swedish has on one’s English. A hypothesis dubbed the Speech Learning Model (SLM) as well as my own hypotheses were used as a base for comparison. LÄS MER

  2. 2. A Data-Driven Approach For Automatic Visual Speech In Swedish Speech Synthesis Applications

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Joel Hagrot; [2019]
    Nyckelord :;

    Sammanfattning : This project investigates the use of artificial neural networks for visual speech synthesis. The objective was to produce a framework for animated chat bots in Swedish. A survey of the literature on the topic revealed that the state-of-the-art approach was using ANNs with either audio or phoneme sequences as input. LÄS MER

  3. 3. Evaluation of Text-Independent and Closed-Set Speaker Identification Systems

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Berk Gedik; [2018]
    Nyckelord :;

    Sammanfattning : Speaker recognition is the task of recognizing a speaker of a given speech record and it has wide application areas. In this thesis, various machine learning models such as Gaussian Mixture Model (GMM), k-Nearest Neighbor(k-NN) Model and Support Vector Machines (SVM) and feature extraction methods such as Mel-Frequency Cepstral Coefficients (MFCC) and Linear Predictive Cepstral Coefficients (LPCC) are investigated for the speaker recognition task. LÄS MER

  4. 4. Developing a spiking neural model of Long Short-Term Memory architectures

    Master-uppsats, Lunds universitet/Fysiska institutionen; Lunds universitet/Förbränningsfysik

    Författare :Isabella Pozzi; [2018]
    Nyckelord :Physics and Astronomy;

    Sammanfattning : Current advances in Deep Learning have shown significant improvements in common Machine Learning applications such as image, speech and text recognition. Specifically, in order to process time series, deep Neural Networks (NNs) with Long Short-Term Memory (LSTM) units are widely used in sequence recognition problems to store recent information and to use it for future predictions. LÄS MER

  5. 5. Classifying Hate Speech using Fine-tuned Language Models

    Master-uppsats, Uppsala universitet/Statistiska institutionen

    Författare :Erik Brorson; [2018]
    Nyckelord :machine learning; natural language processing; hate speech; transfer learning; semi-supervised learning; recurrent neural networks;

    Sammanfattning : Given the explosion in the size of social media, the amount of hate speech is also growing. To efficiently combat this issue we need reliable and scalable machine learning models. Current solutions rely on crowdsourced datasets that are limited in size, or using training data from self-identified hateful communities, that lacks specificity. LÄS MER