Sökning: "speech modelling"

Visar resultat 1 - 5 av 16 uppsatser innehållade orden speech modelling.

  1. 1. Estimating the risk of insurance fraud based on tonal analysis

    Master-uppsats, Lunds universitet/Matematisk statistik

    Författare :Henrik Steneld; [2022]
    Nyckelord :Spectral analysis; Speaker recognition; Tonal analysis; Speaker Diarization; Machine Learning; LSTM; ResNet; Fraud detection; Mathematics and Statistics;

    Sammanfattning : Insurance companies utilize various methods for identifying claims that are of potential fraudulent nature. With the ever progressing field of artificial intelligence and machine learning models, great interest can be found within the industry to evaluate the use of new methods that may arise as a result of new advanced models in combination with the rich data that is being gathered. LÄS MER

  3. 2. Autism i skolan - Beprövade metoder att utveckla skrivförmågan hos elever med autism

    Master-uppsats, Malmö universitet/Institutionen för skolutveckling och ledarskap (SOL)

    Författare :Heike Streblow; [2022]
    Nyckelord :Autism in school; evidence-based methods of developing writing skills; scaffolding; self-contained classrooms;

    Sammanfattning : Abstract Streblow, Heike (2022). Autism in School - Evidence Based Methods to Develop Writing Skills of Students with AutismType of Essay: Master’s thesis (15 credits) Master’s degree, 120 credits, Malmo University, Department of School Development and Leadership Malmo University  There is a great number of international and national studies on younger pupils with autism. LÄS MER

  4. 3. Speaker Recognition using Biology-Inspired Feature Extraction

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

    Författare :Edvin Andersson; [2021]
    Nyckelord :Artificial Intelligence; AI; Machine Learning; Speaker Recognition; Technology and Engineering;

    Sammanfattning : Distinguishing between people's voices is something the human brain does naturally, using only frequencies picked up by the inner ear. The field of speaker recognition is concerned with making machines do the same thing using digitally sampled speech and data processing. LÄS MER

  5. 4. Comparing and contrasting the dissemination cascades of different topics in a social network : What are the lifetimes of different topics and how do they spread

    Kandidat-uppsats, Linköpings universitet/Institutionen för datavetenskap

    Författare :Linus Käll; Simon Pertoft; [2021]
    Nyckelord :spreading; dissemination; topics; topic; modeling; modelling; lda; fake; false; news; social; network;

    Sammanfattning : The web has granted everyone the opportunity to freely share large amounts of data. Individuals, corporations, and communities have made the web an important tool in their arsenal. These entities are spreading information online, but not all of it is constructive. LÄS MER

  7. 5. Wavebender GAN : Deep architecture for high-quality and controllable speech synthesis through interpretable features and exchangeable neural synthesizers

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

    Författare :Gustavo Teodoro Döhler Beck; [2021]
    Nyckelord :Mel-spectrogram; Speech Synthesis; Wavebender GAN; HiFi-GAN; Control- lability; Interpretability; Low-level Signal Properties; Mel-spektrogram; Talsyntes; Wavebender GAN; HiFi-GAN; Kontrollerbarhet; Tolkbarhet; Signalegenskaper På Låg Nivå;

    Sammanfattning : Modeling humans’ speech is a challenging task that originally required a coalition between phoneticians and speech engineers. Yet, the latter, disengaged from phoneticians, have strived for evermore natural speech synthesis in the absence of an awareness of speech modelling due to data- driven and ever-growing deep learning models. LÄS MER