Projects per year
Abstract / Description of output
Since subtitling television content is a costly process, there are large potential advantages to automating it, using automatic speech recognition (ASR). However, training the necessary acoustic models can be a challenge, since the available training data usually lacks verbatim orthographic transcriptions. If there are approximate transcriptions, this problem can be overcome using light supervision methods. In this paper, we perform speech recognition on broadcasts of Weatherview, BBC's daily weather report, as a first step towards automatic subtitling. For training, we use a large set of past broadcasts, using their manually created subtitles as approximate transcriptions. We discuss and and compare two different light supervision methods, applying them to this data. The best training set finally obtained with these methods is used to create a hybrid deep neural network-based recognition system, which yields high recognition accuracies on three separate Weatherview evaluation sets.
Original language | English |
---|---|
Title of host publication | Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 452-457 |
Number of pages | 6 |
ISBN (Print) | 978-1-4799-2756-2 |
DOIs | |
Publication status | Published - 1 Dec 2013 |
Keywords / Materials (for Non-textual outputs)
- learning (artificial intelligence)
- neural nets
- speech recognition
- weather forecasting
- ASR
- Weatherview
- approximate transcriptions
- automatic speech recognition
- daily weather report
- hybrid deep neural network-based recognition system
- light supervision methods
- supervised automatic subtitling
- weather forecasts
- Acoustics
- Speech
- Speech recognition
- Training
- Training data
- Weather forecasting
- Acoustic Model Training
- Light supervision
- Segmentation
- Subtitling
- Transcription
Fingerprint
Dive into the research topics of 'Lightly supervised automatic subtitling of weather forecasts'. Together they form a unique fingerprint.Projects
- 1 Finished