What is word error rate and who is winning?

We love sharing with you more about automated speech transcription.

Word error rate formula 🔧

Word error rate often referred to as WER is a way to measure the performance of an automatic speech recognition (ASR) system. It is tricky to measure because the "ASR result" can have a different length than the "Voice input."

Here is a simple way to understand how WER is calculated:

Sonix - Word Error Rate Formula

To help clarify further, here are some definitions:

Deletion by ASR system:

Voice input: I surf small waves
ASR result: I surf waves

Insertion by ASR system:

Voice input: I surf waves
ASR result: I surf small waves

Substitution by ASR system:

Voice input: I surf small waves
ASR result: I surf all waves

Who is winning? 🏆

Speech recognition technology has come a long way since the 1950s. Our earlier post a short history of speech recognition talks about some of the key events along the way. I talked about how we’ve reached (or almost reached depending on who you talk to) an inflection point in automated speech recognition.

The largest technology companies like Google, IBM, and Microsoft are all clamoring for the accuracy title. Below is the chronology of the claims made in 2017:

Mar 2017: IBM claims 5.5% word error rate
May 2017: Google claims 4.9% word error rate
Aug 2017: Microsoft claims 5.1% word error rate

We’ll continue to update this as new claims are made.

Fast, accurate automated transcription 🚀

Sonix automatically transcribes and translates your audio/video files in 38+ languages. Easily search, edit, and share your media files. Sonix is the best automated transcription software in 2024. Fast, accurate, and affordable. Millions of users from all over the world.

Fast, accurate automated transcription

Includes 30 minutes of free transcription

Other Sonix articles 📃

Tips on how to capture great audio

Hear from other Sonix users about how they record high quality audio

Transcription software

Automated video to text: Convert your audio to text in a few quick steps!

Verbatim transcription

Use cases and benefits of verbatim transcription

Why should you transcribe?

Five reasons you should be transcribing your audio and video files

How much does transcription cost?

The price sometimes varies per hour, minute, or per word

History of speech recognition

How did we get to where we are today in speech recognition? Sonix explains

How to remove the metallic sound

The metallic, tin-like sound you hear in your audio is an unwelcome annoyance

Remove background audio noise

Background noise is annoying and lowers the accuracy of your transcript

Remove background noise in videos

Background noise is distracting in videos and doesn't transcribe well

Room tone: what is it?

Room tone is the naturally occurring noise in the environment during your recording

Audio transcription with Sonix

Sonix is the best online audio transcription service for 2024

Want accurate video transcription?

Sonix is the best online video transcription service. It's fast, accurate, and affordable.

Quickly convert audio to text

We accept over 100 different audio formats. Transcribe with Sonix today.

Transcribe your audio files

We accept many different audio formats (wav, mp3, m4a, ogg, and more)

Transcribe your video files

We accept many video formats (mp4, wma, mov, avi, m4v, and more)

Interview transcription with Sonix

Made for folks who conduct tons of interviews (incl journalists and researchers)

The seven best audio converters

Here are the 7 best free services to convert one audio file format to another

How to make voices sound better

Want to make voices sound more clear in your audio? It's easy.

Remove crosstalk and mic bleed

Make your transcription more accurate by post-processing the audio

How to add subtitles in AVID

The best way to add subtitles and captions to your AVID Media Composer videos

How to mic a two-person interview

Make your transcription more accurate by recording it the right way

Six best tips for transcriptionists

Helping transcriptionists work faster and be more accurate

AI, ML, and NLP

Artificial Intelligence, Machine Learning, and Natural Language Processing

Is voice the next major UI?

We think that it will change how we interact with technology

Word error rate

How do you judge accuracy in the realm of speech recognition?

Free Automated Speech to Text

Sonix: the most accurate automated transcripts for your audio and video

Automatic Video To Text Converter

Sonix gives you the best accuracy when automatically transcribing video to text

A comparison of automation services

Independently reviewed and Sonix scores the highest among automated services

2019 Webby Awards nominee

Top 10% of all sites entered, Top 5 in Machine Learning category

Other Tutorials

Learn how automated transcription unlocks the knowledge in your media files

The best automated transcription service in 2024 🚀

Easily convert your audio to text with Sonix

Sonix automatically transcribes, translates, and helps you organize your audio and video files in over 40 languages. Fast, accurate, and affordable. Millions of users from all over the world.

Try Sonix for freeIncludes 30 minutes of free transcription

Let our support team help you with all of your automated transcription questions. Pictured: Christine Lee

Transcribe and translate confidently, knowing you’re backed by our award-winning team, who is ready to answer your questions. Get immediate help by visiting our Help Center, resources, tutorials, and Introduction to Sonix videos.

Visit our Help Center

You might be interested in 🤔