It has been over 7 months since we published our last speech recognition accuracy benchmark. Back then the results were as follows (from most accurate to least): Microsoft and Amazon (close 2nd), then Voicegain and Google Enhanced, and then, far behind, IBM Watson and Google Standard.

Since then we have obtained more training data and added additional features to our training process. This resulted in a further increase in the accuracy of our model.

As far as the other recognizers are concerned:

• Microsoft and Amazon both improved, with Microsoft improving a lot on the more difficult files from the benchmark set
• Google has released a new model "latest-long" which is quite a bit better than the previous Google's best Video Enhanced model. Accuracy of Video Enhanced stayed pretty much unchanged.

We have decided to no longer report on Google Standard and IBM Watson accuracy, which were always far behind in accuracy.

Methodology

We have repeated the test using similar methodology as before: used 44 files from the Jason Kincaid data set and 20 files published by rev.ai and removed all files where none of the recognizers could achieve a Word Error Rate (WER) lower than 25%.

This time only one file was that difficult. It was a bad quality phone interview (Byron Smith Interview 111416 - YouTube).

‍

The Results

You can see boxplots with the results above. The chart also reports the average and median Word Error Rate (WER)

All of the recognizers have improved (Google Video Enhanced model stayed much the same but Google now has a new recognizer that is better).

Google latest-long, Voicegain, and Amazon are now very close together, while Microsoft is better by about 1 %.

‍

Best Recognizer

Let's look at the number of files on which each recognizer was the best one.

• Microsoft was best on 35 out of the 63 files
• Amazon was best on 15 files (note that in the October 2021 benchmark Amazon was best on 29 files).
• Voicegain was close behind Amazon by being best on 12 audio files
• Google latest-long was best on 4
• Google Video Enhanced wins a participation trophy by being best on 1 file, which was a very easy "The Art of War by Sun Tzu Full" Librivox Audiobook - WER of 1.79%

Note, the numbers do not add to 63 because there were a few files where two recognizers had identical results (to 2 digits behind comma).

‍

Improvements over time

We now have done the same benchmark 4 times so we can draw charts showing how each of the recognizers has improved over the last 1 year and 9 months. (Note for Google the latest result is from latest-long model, other Google results are from video enhanced.)

You can clearly see that Voicegain and Amazon started quite bit behind Google and Microsoft but have since caught up.

Google seems to have the longest development cycles with very little improvement since Sept. 2021 till very recently. Microsoft, on the other hand, releases an improved recognizer every 6 months. Our improved releases are even more frequent than that.

‍

As you can see the field is very close and you get different results on different files (the average and median do not paint the whole picture). As always, we invite you to review our apps, sign-up and test our accuracy with your  data.

‍

Out-of-the-box accuracy is not everything

When you have to select speech recognition/ASR software, there are other factors beyond out-of-the-box recognition accuracy. These factors are, for example:

• Ability to customize the Acoustic Model - Voicegain model may be trained on your audio data - we have several blogposts describing both research and real use-case model customization. The improvements can vary from several percent on more generic cases, to over 50% to some specific cases, in particular for voicebots.
• Ease of integration - Many Speech-to-Text providers offer limited APIs especially for developers building applications that require interfacing with  telephony or on-premise contact center platforms.
• Price - Voicegain is 60%-75% less expensive compared to other Speech-to-Text/ASR software providers while offering almost comparable accuracy. This makes it affordable to transcribe and analyze speech in large volumes.
• Support for On-Premise/Edge Deployment - The cloud Speech-to-Text service providers offer limited support to deploy their speech-to-text software in client data-centers or on the private clouds of other providers. On the other hand, Voicegain can be installed on any Kubernetes cluster - whether managed by a large cloud provider or by the client.

‍

Take Voicegain for a test drive!

1. Click here for instructions to access our live demo site.

2. If you are building a cool voice app and you are looking to test our APIs, click here to sign up for a developer account  and receive $50 in free credits

3. If you want to take Voicegain as your own AI Transcription Assistant to meetings, click here.

‍

Today, we are really excited to announce the launch of Voicegain Transcribe. Transcribe is an AI based transcription assistant for recording and transcription of in-person and web meetings, live video events and webinars. Our goal is to empower users to focus on their meetings/events and leave the note taking to us.

Voicegain Transcribe is built on top of our highly accurate deep-learning-based ASR. It is powered by the same Speech-to-Text APIs that all our developer/platform customers use today. Our out-of-the-box accuracy of 89% is on par with the very best. 

‍
Currently there are 3 main ways you can use Voicegain Transcribe:

1. Transcribe Web Meeting (using browser sharing of audio)

Users can use our browser sharing feature to record & transcribe audio that is playing on any tab on a Chrome or Edge browser. Any meeting platform that allows a browser based client is supported. Some prominent meeting platforms include Google Meet, BlueJeans, Webex and Zoom.

If the Users use a Windows based laptop/desktop, then this Browser sharing supports capturing audio from the client desktop app of the Meeting platform (e.g Zoom or Microsoft Teams). The Mac OS users does not support sharing of audio from a desktop app with Voicegain Transcribe.

2. Microphone Capture

This allows users to record and transcribe anything that is captured by the microphone on their laptop/desktop. So Users can turn on the microphone capture for an in- person meeting, lecture or event. They can also just let a web meeting or event play on their speaker and have the microphone capture what is being played on it.

3. Upload Audio Recordings

Users may also upload pre-recorded audio files of their meetings, podcasts, calls and generate the transcript. We support over 40 different formats including mp3, mp4, wav, aac and ogg). Voicegain supports speaker diarization - so we can separate speakers even on a single channel audio recording.

‍

Languages Supported

Currently we support English and Spanish. More languages are in our roadmap - German, Portuguese, Hindi.

‍

Advanced Features

Voicegain Transcribe also supports the following advanced Features.‍

a. Projects

Users can organize their meeting recordings and audio files into different projects. A project is like a workspace or a folder.‍

b. Named Entities & Keywords

Users can highlight named entities (dates, currency, addresses, email id) in their meeting transcript.

c. PII Redaction

Users can also mask - in both text and audio - any personally identifiable information.

Coming Soon

We are adding close integration with the Zoom meeting platform. With this, we can capture the actual speaker labels directly from Zoom. This will address errors related to diarization.

We are also adding a Chrome extension that will make it much easier to record and transcribe web meetings.

Get Started for Free today!

By signing up today, you will be signed up on our forever Free Plan - which makes you eligible for 120 mins of Meeting Transcription free every month . Once you are  satisfied with our accuracy and our user experience, you can easily upgrade to Paid Plans.

If you have any questions, please email us at support.transcribe@voicegain.ai

‍