Preprint
Measuring the Accuracy of Automatic Speech Recognition Solutions
Korbinian Kuhn et al., arXiv (preprint), 2024
Read the originalRead on October 16, 2026
- What it is
- A 2024 study from Stuttgart Media University that tested eleven common automatic speech recognition services on recordings of higher education lectures, including streaming (live) and non-streaming modes.
- How much weight it carries
- Preprint, not yet confirmed as a journal article when checked. It uses lecture recordings rather than conversation or noisy rooms, and the authors compare services on the same samples.
Facts taken from this source
- In a 2024 study of eleven speech recognition services on university lecture recordings, Google's average word error rate on English was 20.1 percent.
“Google 20.1 23.6 28.1 18.1 IBM 11.2 13.2 17.3 20.6” (Table 4, English column)
- The same 2024 study found significantly lower quality for streaming speech recognition, the mode used for live events.
“We also measured a significant lower quality for streaming ASR, which is used for live events.” (Abstract)
- A 2024 study of eleven common speech recognition services on university lecture recordings found accuracy varied widely between vendors and between individual recordings.
“Our results show that accuracy ranges widely between vendors and for the individual audio samples.” (Abstract)
- In the same 2024 study, Whisper large-v2 had an average word error rate of 2.9 percent on the English lecture recordings.
“Speechmatics 3.3 3.6 4.6 8.0 Tencent 4.6 4.1 7.3 - Whisper (large-v2) 2.9 3.3 3.3 5.0” (Table 4)
Pages that rest on this source
- Zoom, Teams and Google Meet TranscriptionGuide
- Transcription Software: How to Choose OneGuide
- Speech Recognition in Python: Libraries ComparedGuide
- How do you transcribe a lecture recording?Question
- How do you transcribe a Zoom audio or video recording?Question
- Is Whisper more accurate than Google Speech-to-Text?Question
- How Speech Recognition Works, From Sound to TextGuide
- Speech-to-Text APIs Compared: Price, Accuracy, SpeedGuide
- Speech to Text for Deaf and Hard of Hearing PeopleGuide
- Do speech to text glasses work for deaf people?Question
- Is automatic captioning accurate enough for deaf people?Question
- Is speech recognition more accurate than humans?Question
- Which speech-to-text API is the best?Question
- Video to Text: Transcribe Videos and YouTubeGuide
- What is IBM Watson Speech to Text?Question