Sökning: "Taligenkänning"
Visar resultat 1 - 5 av 69 uppsatser innehållade ordet Taligenkänning.
1. Identification and Classification of TTS Intelligibility Errors Using ASR : A Method for Automatic Evaluation of Speech Intelligibility
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In recent years, applications using synthesized speech have become more numerous and publicly available. As the area grows, so does the need for delivering high-quality, intelligible speech, and subsequently the need for effective methods of assessing the intelligibility of synthesized speech. LÄS MER
2. Implementing UX/UI in a real-time speech recognition and translation application in Android and a clinical study
Uppsats för yrkesexamina på grundnivå, Umeå universitet/Institutionen för tillämpad fysik och elektronikSammanfattning : According to WHO(World Health Organization) there are over 1,5 billion people living with hearing loss. Furthermore, HRF(Hörselskadades riksförbund) believe that ‘hidden hearing loss’ can be a much larger scale of the population than what was believed. There are two parts in this project taking place parallel. LÄS MER
3. En undersökning av AI-verktyget Whisper som potentiell ersättare till det manuella arbetssättet inom undertextframtagning
M1-uppsats, KTH/Hälsoinformatik och logistikSammanfattning : Det manuella arbetssättet för undertextframtagning är en tidskrävande och kostsam process. Arbetet undersöker AI-verktyget Whisper och dess potential att ersätta processen som används idag. Processen innefattar både transkribering och översättning. LÄS MER
4. 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
5. Improving accuracy of speech recognition for low resource accents : Testing the performance of fine-tuned Wav2vec2 models on accented Swedish
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : While the field of speech recognition has recently advanced quickly, even the highest performing models struggle with accents. There are several methods of improving the performance on accents, but many are hard to implement or need high amounts of data and are therefore costly to implement. LÄS MER