Sökning: "Speech Learning Model"

Visar resultat 1 - 5 av 34 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. Implementation of an 8-bit Dynamic Fixed-Point Convolutional Neural Network for Human Sign Language Recognition on a Xilinx FPGA Board

    Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknik

    Författare :Ricardo Núñez-Prieto; [2019]
    Nyckelord :Artificial Intelligence; Computer Vision; Machine Learning; Convolutional Neural Networks; FPGA; Sign Language Recognition; Technology and Engineering;

    Sammanfattning : The goal of this thesis work is to implement a convolutional neural network on an FPGA device with the capability of recognising human sign language. The set of gestures that the neural network can identify has been taken from the Swedish sign language, and it consists of the signs used for representing the letters of the Swedish alphabet (a.k.a. LÄS MER

  3. 3. 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

  4. 4. 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

  5. 5. 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