Sökning: "word recognition"
Visar resultat 11 - 15 av 110 uppsatser innehållade orden word recognition.
11. The role of word accents in semantic processing in South Swedish
Master-uppsats, Lunds universitet/Masterprogram: Språk och språkvetenskap; Lunds universitet/FonetikSammanfattning : Prosodic cues can aid speech processing by adding semantic information in lexical tones or functional information in intonational tones. Swedish word accents are considered to have stronger grammatical functions than semantic roles, although they are shaped by both lexical and intonational information structure. LÄS MER
12. Handwritten Text Recognition Using a Vision Transformer
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : The aim of this project is to create a method for offline handwritten text recognition using a vision transformer. It consists of two parts, where the first one segments all words in a document into separate images and the second one which recognizes the word on each image. LÄS MER
13. Generation of Control Logic from Ordinary Speech
Kandidat-uppsats, Högskolan i Halmstad/Akademin för informationsteknologiSammanfattning : Developments in automatic code generation are evolving remarkably fast, with companies and researchers competing to reach human-level accuracy and capability. Advancements in this field primarily focus on using machine learning models for end-to-end code generation. LÄS MER
14. WebXR Voice Assistant : A comparative study of automatic speech recognition implementation methods in a web-based VR environment
Uppsats för yrkesexamina på avancerad nivå, Mittuniversitetet/Institutionen för informationssystem och –teknologiSammanfattning : Fully autonomous cars are on the horizon. Knightec wants to enable passengers of the future car to be more productive and entertained with a new web platform. With this platform, Knightec wants to explore different input methods one of which being a voice assistant. LÄS MER
15. Domain Adaptation with N-gram Language Models for Swedish Automatic Speech Recognition : Using text data augmentation to create domain-specific n-gram models for a Swedish open-source wav2vec 2.0 model
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Automatic Speech Recognition (ASR) enables a wide variety of practical applications. However, many applications have their own domain-specific words, creating a gap between training and test data when used in practice. LÄS MER