Sökning: "speech errors"

Visar resultat 1 - 5 av 40 uppsatser innehållade orden speech errors.

  1. 1. Speech Fluency and Ageing

    Kandidat-uppsats, Lunds universitet/Avdelningen för lingvistik och kognitiv semiotik; Lunds universitet/Allmän språkvetenskap

    Författare :Harry Polfeldt; [2022]
    Nyckelord :fluency; age; ageing; aging; linguistics; language; disfluencies; disfluency; dysfluency; dysfluencies; speech; error; errors; psycholinguistics; pause; pauses; repetition; repetitions; lengthening; lengthenings; prolongation; prolongations; swedish; interruption; interruptions; filled; unfilled; unfilled pause; unfilled pauses; filled pause; filled pauses; speech error; speech errors; speech fluency; Languages and Literatures;

    Sammanfattning : Several physiological changes in the speech production process in old age have been documented, yet studies of cognitive changes are few and inconclusive. The current study investigates changes in rates of disfluencies, rates of speech errors and speech rate to examine if speech fluency changes throughout the adult lifespan, as well as whether the influence of task complexity on fluency remains constant regardless of the age of the speaker. LÄS MER

  2. 2. Cross-lingual and Multilingual Automatic Speech Recognition for Scandinavian Languages

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

    Författare :Rafal Černiavski; [2022]
    Nyckelord :cross-lingual; multilingual; automatic speech recognition; ASR;

    Sammanfattning : Research into Automatic Speech Recognition (ASR), the task of transforming speech into text, remains highly relevant due to its countless applications in industry and academia. State-of-the-art ASR models are able to produce nearly perfect, sometimes referred to as human-like transcriptions; however, accurate ASR models are most often available only in high-resource languages. LÄS MER

  3. 3. Automatic Podcast Chapter Segmentation : A Framework for Implementing and Evaluating Chapter Boundary Models for Transcribed Audio Documents

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

    Författare :Adam Feldstein Jacobs; [2022]
    Nyckelord :Machine Learning; Natural Language Processing; Speech Technology; Deep Learning; Podcast Segmentation; Maskininlärning; Språkteknologi; Djupinlärning; Podcast Segmentation;

    Sammanfattning : Podcasts are an exponentially growing audio medium where useful and relevant content should be served, which requires new methods of information sorting. This thesis is the first to look into the state-of-art problem of segmenting podcasts into chapters (structurally and topically coherent sections). LÄS MER

  4. 4. Medical image captioning based on Deep Architectures

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

    Författare :Georgios Moschovis; [2022]
    Nyckelord :Artificial Neural Networks; Deep Learning; Speech and language technology; Natural Language Processing NLP ; Deep networks; Generative deep networks; Convolutional neural networks CNN ; Text generation; Information retrieval; Diagnostic captioning; Image captioning; concept prediction; classification; image encoders; transformers; Encoder-Decoder architecture; abstractive summarization; Neurala nätverk; Djup inlärning; Tal-och språkteknologi; naturlig språkbehandling; djup neurala nätverk; generativa djupa nätverk; konvolutionella neurala nätverk; Textgenerering; Informationssökning; Diagnostisk textning; Bildtextning; konceptförutsägelse; klassificering; bildkodare; transformatorer; kodaravkodararkitektur; abstrakt sammanfattning;

    Sammanfattning : Diagnostic Captioning is described as “the automatic generation of a diagnostic text from a set of medical images of a patient collected during an examination” [59] and it can assist inexperienced doctors and radiologists to reduce clinical errors or help experienced professionals increase their productivity. In this context, tools that would help medical doctors produce higher quality reports in less time could be of high interest for medical imaging departments, as well as significantly impact deep learning research within the biomedical domain, which makes it particularly interesting for people involved in industry and researchers all along. LÄS MER

  5. 5. Cognate effects in intra-sentential codeswitching in trilinguals - evidence from a read-aloud task

    Master-uppsats, Lunds universitet/Masterprogram: Språk och språkvetenskap; Lunds universitet/Allmän språkvetenskap

    Författare :Annika Milena Schimpff; [2021]
    Nyckelord :cognates; codeswitching; read-aloud task; language processing; language activation; speech monitoring; planned speech production; Languages and Literatures;

    Sammanfattning : This thesis examines the effect of cognates on codeswitching in planned speech production in trilinguals, which has previously been unexplored. Previous studies on cognates and codeswitching have primarily focused on cognate facilitation effects in spontaneous speech in bilinguals. LÄS MER