Sökning: "automatic transcription"
Visar resultat 1 - 5 av 28 uppsatser innehållade orden automatic transcription.
1. A Comparative Analysis of Whisper and VoxRex on Swedish Speech Data
Kandidat-uppsats, Uppsala universitet/Statistiska institutionenSammanfattning : With the constant development of more advanced speech recognition models, the need to determine which models are better in specific areas and for specific purposes becomes increasingly crucial. Even more so for low-resource languages such as Swedish, dependent on the progress of models for the large international languages. LÄS MER
2. Evaluating and Fine-Tuning a Few-Shot Model for Transcription of Historical Ciphers
Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologiSammanfattning : Thousands of historical ciphers, encrypted manuscripts, are stored in archives across Europe. Historical cryptology is the research field concerned with studying these manuscripts - combining the interest of humanistic fields with methods of cryptography and computational linguistics. LÄS MER
3. aiLangu - Real-time Transcription and Translation to Reduce Language Barriers : An Engineering Project to Develop an Application for Enhancing Human Verbal Communication
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The research area this report relates to is real-time automatic transcription and translation. The purpose of the work done for the report is to reduce the perceived language barriers online and to make a user-friendly application to make use of the latest deep learning technology to transcribe and translate in real-time. LÄS MER
4. Automatic Voice Trading Surveillance : Achieving Speech and Named Entity Recognition in Voice Trade Calls Using Language Model Interpolation and Named Entity Abstraction
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen Vi3Sammanfattning : This master thesis explores the effectiveness of interpolating a larger generic speech recognition model with smaller domain-specific models to enable transcription of domain-specific conversations. The study uses a corpus within the financial domain collected from the web and processed by abstracting named entities such as financial instruments, numbers, as well as names of people and companies. LÄS MER
5. En utvärdering av tjänster för taligenkänning och textsammanfattning och möjligheter att skapa undertexter i filmer.
M1-uppsats, KTH/Hälsoinformatik och logistikSammanfattning : Att skapa undertexter till filmer är idag ett hantverk som är en tidskrävande process. Företaget Firstlight Media textar cirka 200 filmer per vecka helt manuellt och var av en film tar cirka 4–6 timmar att färdigställa. Skulle man kunna automatisera delar av processen för att undertexta filmer finns det möjlighet att spara resurser. LÄS MER