Advanced search

Showing result 1 - 5 of 9 essays matching the above criteria.

1. 1. A Comparative Analysis of Whisper and VoxRex on Swedish Speech Data

   University essay from Uppsala universitet/Statistiska institutionen

   Author : Max Fredriksson; Elise Ramsay Veljanovska; [2024]
   Keywords : ASR; Automatic Speech Recognition; Swedish Speech Recognition; Speech Recognition Models; Speech-to-Text; Whisper; VoxRex; Wav2Vec; Model Comparison; Transformer Models; Neural Networks; Machine Learning; WER; Word Error Rate; Transcription;

   Abstract : 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. READ MORE

3. 2. Improving accuracy of speech recognition for low resource accents : Testing the performance of fine-tuned Wav2vec2 models on accented Swedish

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Arash Dabiri; [2023]
   Keywords : Speech-to-text; deep learning; accents; wav2vec; tal-till-text; djupinlärning; brytningar; wav2vec;

   Abstract : 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. READ MORE

4. 3. 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

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Viktor Enzell; [2022]
   Keywords : Automatic Speech Recognition; Domain Adaptation; Language Models; Ngram Models; Wav2vec2; Taligenkänning; Domänanpassning; Språkmodeller; N-gramModeller; Wav2vec2;

   Abstract : 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. READ MORE

5. 4. A Swedish wav2vec versus Google speech-to-text

   University essay from Uppsala universitet/Statistiska institutionen

   Author : Ester Lagerlöf; [2022]
   Keywords : ASR; automatic speech recognition; speech-to-text; wav2vec; Google speech-to-text; model comparison;

   Abstract : As the automatic speech recognition technology is becoming more advanced, the possibilities of in which fields it can operate are growing. The best automatic speech recognition technologies today are mainly based on - and made for - the English language. READ MORE

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

   University essay from Uppsala universitet/Institutionen för lingvistik och filologi

   Author : Rafal Černiavski; [2022]
   Keywords : cross-lingual; multilingual; automatic speech recognition; ASR;

   Abstract : 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. READ MORE