Sökning: "Speaker identification"

Visar resultat 1 - 5 av 16 uppsatser innehållade orden Speaker identification.

  1. 1. Solar Panel Protectionfrom Birds and Land Animals

    Kandidat-uppsats, Blekinge Tekniska Högskola/Institutionen för matematik och naturvetenskap

    Författare :Omkar Siddeswar Tenali; Jyothish Chandra Narayana Sri Ranga; [2023]
    Nyckelord :Bird detection; Camera; Raspberry Pi; Speaker; Solar Panel.;

    Sammanfattning : Context: Nowadays, there are many sources to generate electricity, but most of the resources used are not renewable. Among the renewable energies generated, solar power is one of the best. However, solar panels need to be protected from birds and other animals, which can cause damage. LÄS MER

  3. 2. Analysis of speaking time and content of the various debates of the presidential campaign : Automated AI analysis of speech time and content of presidential debates based on the audio using speaker detection and topic detection

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

    Författare :Axel Valentin Maza; [2023]
    Nyckelord :Artificial Intelligence; Speaker detection; Speaker recognition; Speaker diarization; Speaker identification; Debate; Politics; Deep Learning; Artificiell intelligens; talardetektion; talarigenkänning; talardiarisering; talaridentifiering; debatt; politik; djupinlärning;

    Sammanfattning : The field of artificial intelligence (AI) has grown rapidly in recent years and its applications are becoming more widespread in various fields, including politics. In particular, presidential debates have become a crucial aspect of election campaigns and it is important to analyze the information exchanged in these debates in an objective way to let voters choose without being influenced by biased data. LÄS MER

  4. 3. How do voiceprints age?

    Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

    Författare :Maya Konstantinovna Nachesa; [2023]
    Nyckelord :Voiceprint; Speaker Emotion Recognition; Age; Speaker Verification;

    Sammanfattning : Voiceprints, like fingerprints, are a biometric. Where fingerprints record a person's unique pattern on their finger, voiceprints record what a person's voice "sounds like", abstracting away from what the person said. They have been used in speaker recognition, including verification and identification. LÄS MER

  5. 4. Evaluation of Methods for Sound Source Separation in Audio Recordings Using Machine Learning

    Master-uppsats, Linköpings universitet/Kommunikationssystem

    Författare :Amanda Gidlöf; [2023]
    Nyckelord :Sound source separation; signal processing; audio processing; speech enhancement; speaker identification; speech separation; speech processing; speaker separation; single channel; multi channel; cocktail party problem; machine learning; neural network; deep learning; deep neural network; convolutional network; dual-path network; filter-and-sum network; recurrent network; beamforming;

    Sammanfattning : Sound source separation is a popular and active research area, especially with modern machine learning techniques. In this thesis, the focus is on single-channel separation of two speakers into individual streams, and specifically considering the case where two speakers are also accompanied by background noise. LÄS MER

  7. 5. Contact-induced change and variation in Middle English morphology : A case study on get

    Kandidat-uppsats, Stockholms universitet/Engelska institutionen

    Författare :Johanna Åberg; [2021]
    Nyckelord :Language contact; Language change; Middle English; Old Norse; Cognitive linguistics; Old English.;

    Sammanfattning : The present study explores the role of interlingual identification in contact between speakers of Old Norse and Old English. The study focuses on the word get as it occurred throughout a selection of texts in the Middle English period. LÄS MER