Broadcast News Summarization
With the growing importance of Internet, there is a constantly growing amount of multimedia being generated, such as broadcast tv and radio programs, vlogs, etc.
Being able to efficiently summarize the content of such sources of information has the potential to affect various sectors. The primary carrier of information in such sources is speech. Thus, the broadcast news processing is essentially an extractive speech summarization. It involves tasks such as Automatic Speech Recognition, Topic Segmentation, Extractive Summarization; and other tasks, such as Sentiment Analysis, to enhance the value of the summary.
The broadcast news processing consists in the following automated tasks:
- Automatic transcription of the audio of the news
- Segmentation of the broadcast into topical segments (news)
- Extraction of the key phrases form the news segments
- Extractive summarization of the news segments
- Sentiment Analysis of news segments
- Topic and sentiment trend analysis
Everyday one of our servers automatically downloads and processes broadcast news from LA7 Youtube Channel. Extracted information is then exposed in a friendly User Interface using sections, color-coding and animation effects. Additionally, Sentiment Trend of news is constructed using the daily news broadcasts.