Chapter
Factors Affecting Automatic Speech Recognition Accuracy
30:48 - 35:50 (05:02)
The quality of the audio is a key factor in determining the accuracy of automatic speech recognition. The use of the DSR tool may not work effectively when the speaker is too far away or when there is a lot of cross talk.
Clips
The founder of Revvers, a transcription and captioning service for podcasts, talks about the tools available to podcasters to make production better for their target audience.
30:48 - 32:19 (01:31)
Summary
The founder of Revvers, a transcription and captioning service for podcasts, talks about the tools available to podcasters to make production better for their target audience.
ChapterFactors Affecting Automatic Speech Recognition Accuracy
Episode#151 – Dan Kokotov: Speech Recognition with AI and Humans
PodcastLex Fridman Podcast
The accuracy of speech recognition technology depends on the quality of the audio.
32:20 - 33:13 (00:52)
Summary
The accuracy of speech recognition technology depends on the quality of the audio. While real-time transcription is possible, it can be difficult due to the complex process of transcribing speech accurately.
ChapterFactors Affecting Automatic Speech Recognition Accuracy
Episode#151 – Dan Kokotov: Speech Recognition with AI and Humans
PodcastLex Fridman Podcast
A 14% word error rate is currently considered the world's best Automatic Speech Recognition (ASR) for this kind of speech, which measures the percentage of words that are incorrectly transcribed.
33:14 - 35:50 (02:36)
Summary
A 14% word error rate is currently considered the world's best Automatic Speech Recognition (ASR) for this kind of speech, which measures the percentage of words that are incorrectly transcribed.