IMS-Speech: A Speech to Text Tool
This tool addresses the need for accessible speech-to-text transcription in academic research, though it is incremental as it applies existing methods to new language data.
The authors developed IMS-Speech, a web-based tool for German and English speech transcription to support research requiring lexical access in spoken language, built using open-source software and public data to achieve competitive accuracy across diverse tasks.
We present the IMS-Speech, a web based tool for German and English speech transcription aiming to facilitate research in various disciplines which require accesses to lexical information in spoken language materials. This tool is based on modern open source software stack, advanced speech recognition methods and public data resources and is freely available for academic researchers. The utilized models are built to be generic in order to provide transcriptions of competitive accuracy on a diverse set of tasks and conditions.