Sökning: "taligenkänning"

Visar resultat 1 - 5 av 47 uppsatser innehållade ordet taligenkänning.

  1. 1. ATT GÖRA SIN RÖST HÖRD Hur fungerar tal-till-text-verktyg som skrivhjälpmedel för personer med afasi?

    Magister-uppsats, Göteborgs universitet/Institutionen för neurovetenskap och fysiologi

    Författare :Hanna Hansson; Magdalena Andersson; [2021-02-12]
    Nyckelord :afasi; automatisk taligenkänning; skrivande; tal-till-text-verktyg; digitala hjälpmedel; aphasia; automatic speech recognition; writing; speech-to-text-technology; digital assistive technology;

    Sammanfattning : This study aimed to investigate if speech-to-text-technology could facilitate writing for people with aphasia, and if there was a difference in dictation accuracy between two persons with aphasia and two persons without known neurological disease. Dictation accuracy is how correctly the speech-to-text-technology transcribed what was spoken. LÄS MER

  3. 2. Experiments in speaker diarization using speaker vectors

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

    Författare :Ming Cui; [2021]
    Nyckelord :Speaker Diarization; Embedding Extraction Module; Deep Learning; Supervised method; Unsupervised method; Talardiarisering; inbäddning av extraktionsmodul; djupinlärning; övervakad metod; oövervakad metod;

    Sammanfattning : Speaker Diarization is the task of determining ‘who spoke when?’ in an audio or video recording that contains an unknown amount of speech and also an unknown number of speakers. It has emerged as an increasingly important and dedicated domain of speech research. LÄS MER

  4. 3. Self-Learning Methodology for Failure Detection in an Oil- Hydraulic Press : Predictive maintenance

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

    Författare :Diego Alonso Guillen Rosaperez; [2020]
    Nyckelord :Signal Processing; Deep Learning; Machine Learning; Predictive Maintenance; Anomaly Detection.; Signalbehandling; djupinlärning; maskininlärning; förutsägbart underhåll; upptäckt av avvikelser.;

    Sammanfattning : Deep Learning methods have dramatically improved the state-of-the-art across multiple fields, such as speech recognition, object detection, among others. Nevertheless, its application on signal processing, where data is frequently unlabelled, has received relatively little attention. LÄS MER

  5. 4. Robust Speech Activity Detection and Direction of Arrival Using Convolutional Neural Networks

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

    Författare :Anton Näslund; Charlie Jeansson; [2020]
    Nyckelord :Speech Activity Detection SAD ; ConvolutionNeural Networks CNN ; CMU Artic; Pyroomacustic; VoiceActivity Detection VAD .;

    Sammanfattning : Social robots are becoming more and more common in our everyday lives. In the field of conversational robotics, the development goes towards socially engaging robots with humanlike conversation. This project looked into one of the technical aspects when recognizing speech, videlicet speech activity detection (SAD). LÄS MER

  7. 5. Normalizing Flow based Hidden Markov Models for Phone Recognition

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

    Författare :Anubhab Ghosh; [2020]
    Nyckelord :Phone recognition; generative learning; Normalizing flows; Decision fusion; Speech recognition;

    Sammanfattning : The task of Phone recognition is a fundamental task in Speech recognition and often serves a critical role in bench-marking purposes. Researchers have used a variety of models used in the past to address this task, using both generative and discriminative learning approaches. LÄS MER