Sökning: "dator tal"

Visar resultat 1 - 5 av 20 uppsatser innehållade orden dator tal.

  1. 1. Performance analysis of on- device streaming speech recognition

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

    Författare :Martin Köling; [2021]
    Nyckelord :streaming speech recognition; attention; end-to-end; transformer; conformer; on- device inference; machine learning; strömmande taligenkänning; attention; end-to-end; transformer; conformer; on- device slutledning; maskininlärning;

    Sammanfattning : Speech recognition is the task where a machine processes human speech into a written format. Groundbreaking scientific progress within speech recognition has been fueled by recent advancements in deep learning research, improving both key metrics of the task; accuracy and speed. LÄS MER

  3. 2. Evaluation of float-truncation based compression techniques for the ATLAS jet trigger

    Kandidat-uppsats, Lunds universitet/Partikel- och kärnfysik; Lunds universitet/Fysiska institutionen

    Författare :Love Kildetoft; [2021]
    Nyckelord :Physics and Astronomy;

    Sammanfattning : Data compression methods allow more data to be stored within a certain storage framework while still keeping the characteristics of the data in question. At the Large Hadron Collider on the grounds of CERN in Switzerland, limited data storage capability is and has always been an urgent problem. LÄS MER

  4. 3. Teknik för dokumentering avmöten och konferenser

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

    Författare :Milan Stojanovic; [2019]
    Nyckelord :Speech-to-text; Speaker recognition; Software development; Architechture; Design; Conference tool; Tal-till-text; Talarigenkänning; Systemutveckling; Arkitektur; Design; Konferensverktyg;

    Sammanfattning : Documentation of meetings and conferences is performed at most companies by one or more people sitting at a computer and typing what has been said during the meeting. This may lead to typing mistakes or incorect perception by the person who records. The human factor is quite large. LÄS MER

  5. 4. Latent Space Growing of Generative Adversarial Networks

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Erik Sandström; [2019]
    Nyckelord :Generative models; GAN; Generative Adversarial Networks; Artificial Intelligence; CelebA; Latent Space; Deep Learning; Computer Vision; Machine Learning; Mathematics and Statistics;

    Sammanfattning : This thesis presents a system, which builds on the Generative Adversarial Network (GAN) framework, with the focus of learning interpretable representations of data. The system is able to learn representations of data that are ordered in regards to the saliency of the attributes, in a completely unsupervised manner. LÄS MER

  7. 5. On the Effectiveness of Handcrafted and Learned Features in Automated Essay Scoring

    Master-uppsats, Lunds universitet/Beräkningsbiologi och biologisk fysik - Genomgår omorganisation

    Författare :Edvin Jakobsson; [2019]
    Nyckelord :Natural Language Processing Machine Learning Automated Essay Scoring; Technology and Engineering;

    Sammanfattning : The task of Automated Essay Scoring (AES) has been active for more than half a century, starting with handcrafting statistical features used for linear regression, and currently being improved by the latest advancements in machine learning and natural language processing. Most current research uses some form of character or word embeddings to represent the essays rather than statistical features, enabling the models to analyze the text in full and automatically learn what to look for. LÄS MER