Sökning: "Speech Learning Model"
Visar resultat 6 - 10 av 100 uppsatser innehållade orden Speech Learning Model.
6. Punctuation Restoration as Post-processing Step for Swedish Language Automatic Speech Recognition
Magister-uppsats, Luleå tekniska universitet/Institutionen för system- och rymdteknikSammanfattning : This thesis focuses on the Swedish language, where punctuation restoration, especially as a postprocessing step for the output of Automatic Speech Recognition (ASR) applications, needs furtherresearch. I have collaborated with NewsMachine AB, a company that provides large-scale mediamonitoring services for its clients, for which it employs ASR technology to convert spoken contentinto text. LÄS MER
7. Sentence Stress in Songs: The Potential of Using Authentic Songs for Teaching English Sentence Stress to EFL Learners in Swedish Lower-Secondary School
L3-uppsats, Lunds universitet/Avdelningen för engelska; Lunds universitet/EngelskaSammanfattning : Using music as a tool for teaching a foreign language has been shown to positively affect the language learning process (Balčytytė-Kurtinienė, 2018; Cañete García et al., 2022; Heidari- Shahreza & Moinzadeh, 2012), and this essay suggests that authentic English songs can be used in the teaching of EFL in lower-secondary school in Sweden to efficiently meet many aspects of the syllabus. LÄS MER
8. Diffusion-based Vocoding for Real-Time Text-To-Speech
Master-uppsats, Lunds universitet/Matematisk statistikSammanfattning : The emergence of machine learning based text-to-speech systems have made fully automated customer service voice calls, spoken personal assistants, and the creation of synthetic voices seem well within reach. However, there are still many technical challenges with creating such a system which can generate audio quickly and of high enough quality. LÄS MER
9. Deep convolution neural network for attention decoding in multi-channel EEG with conditional variational autoencoder for data augmentation
Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Institutionen för reglerteknikSammanfattning : Objectives: This project aims to develop a deep learning-based attention decoding system that can distinguish between noise and speech in noise and also identify the direction of attended speech from the brain data recorded with electroencephalography (EEG) instruments. Two deep convolutional neural network (DCNN) models will be designed: (1) one DCNN model capable of classifying incoming segments of sound as speech or speech in background noise, and (2) one DCNN model identifying the direction (left vs. LÄS MER
10. Mispronunciation Detection with SpeechBlender Data Augmentation Pipeline
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The rise of multilingualism has fueled the demand for computer-assisted pronunciation training (CAPT) systems for language learning, CAPT systems make use of speech technology advancements and offer features such as learner assessment and curriculum management. Mispronunciation detection (MD) is a crucial aspect of CAPT, aimed at identifying and correcting mispronunciations in second language learners’ speech. LÄS MER