Many humanities scholars are well versed with hermeneutic analysis, but lack knowledge required to understand the tools necessary to work with spoken word data in the digital age. In digital research using speech data, a lot of specific digital methods are used with corresponding jargon.
The articles within this category will provide researchers a basic overview of some digital technologies that one might encounter when approaching speech data with digital tools. At the end a glossary is provided, filled with jargon related to digital speech analysis.
In the coming pages, the following digital technologies will be considered:
- Speech Recognition: the automatic conversion of spoken word to typed text.
- Forced Alignment: aligning typed text with the time words are spoken in the audio file.
- G2P: Grapheme-to-Phomene, or technology that converts typed ortographic text to the phonetic representation of that text.
- Text Analytics: converting unstructured text data into meaningful data for analysis.
- Subtitles: the ways in which the technology around subtitles can be useful in analysing speech data.
- OCR: Optical Character Recognition, the technology that converts images of text in to typed digital text.
In the next category, named ‘Tools’, some tools that use these different technologies are exemplified.