A couple of months back, we had launched the Kookoo <recognize> tag. And as mentioned in the blog post, we support the Google speech engine and our very own Zena engine.
The Kookoo speech engine as it currently stands is just a drop in the ocean when compared to the features provided by the Google speech engine. But, as they say, a journey of a thousand miles starts with a single step. This post is about our first step.
As of today, we are launching our first model, the Yes/No model, built in house, based on a proprietary AI algorithm . You can now design your Kookoo IVRs to say "Please say yes or no", instead of "Please press 1 for yes and 2 for no".
In the internal tests our model's accuracy has been so good, we believe that this can become the standard interaction mechanism instead of DTMF.
We also did a side by side comparison of our model with Google's speech API. Before presenting the results below, some disclaimers:
1. Our model is a specific model for Yes/No. Google's model is more of a generic ASR. And in most cases specific models work better than generic models.
2. Google's ASR is in the cloud. Though our model is also in the cloud, since its co hosted with Kookoo, Kookoo responses will generally be faster.
3. Our model has not yet been fine tuned for negative cases. So, it detects only yes or no.
The data sets used for the testing in the experiments are the yes and no examples from the Google speech commands dataset. Our yes/no model was not trained with any of the samples in that dataset.
Experiment 1:
Converted dataset to 8Khz to fit the telephony format.
Google API accuracy: 78.437%
Kookoo Zena accuracy: 96.5%
We felt the accuracy for Google dropped down because of the 8Khz format. So we did another experiment for Google speech API.
Experiment 2:
Original speech command dataset
Google API accuracy: 92%
We also ran the test on multiple other private data sources. In all the cases Kookoo Zena out performed Google speech API.
We have setup a demo number for you to test it out. Please dial
The configuration used for Google speech api:
{
"config": {
"profanity_filter": false,
"encoding": "LINEAR16",
"speech_contexts": {"phrases":["yes","no"]},
"max_alternatives": 1,
"sample_rate_hertz": 8000/16000,
"language_code": "en-IN",
"enable_word_time_offsets": true
}
}
The Kookoo speech engine as it currently stands is just a drop in the ocean when compared to the features provided by the Google speech engine. But, as they say, a journey of a thousand miles starts with a single step. This post is about our first step.
As of today, we are launching our first model, the Yes/No model, built in house, based on a proprietary AI algorithm . You can now design your Kookoo IVRs to say "Please say yes or no", instead of "Please press 1 for yes and 2 for no".
In the internal tests our model's accuracy has been so good, we believe that this can become the standard interaction mechanism instead of DTMF.
We also did a side by side comparison of our model with Google's speech API. Before presenting the results below, some disclaimers:
1. Our model is a specific model for Yes/No. Google's model is more of a generic ASR. And in most cases specific models work better than generic models.
2. Google's ASR is in the cloud. Though our model is also in the cloud, since its co hosted with Kookoo, Kookoo responses will generally be faster.
3. Our model has not yet been fine tuned for negative cases. So, it detects only yes or no.
The data sets used for the testing in the experiments are the yes and no examples from the Google speech commands dataset. Our yes/no model was not trained with any of the samples in that dataset.
Experiment 1:
Converted dataset to 8Khz to fit the telephony format.
Google API accuracy: 78.437%
Kookoo Zena accuracy: 96.5%
We felt the accuracy for Google dropped down because of the 8Khz format. So we did another experiment for Google speech API.
Experiment 2:
Original speech command dataset
Google API accuracy: 92%
We also ran the test on multiple other private data sources. In all the cases Kookoo Zena out performed Google speech API.
We have setup a demo number for you to test it out. Please dial
080-4920 2086(India)
This is a simple demo, which will ask you to say yes or no and then play the result as per Kookoo and then ask you to say yes or no again and play the result by Google. The demo was built using the Kookoo <recognize> tag.
And this is just the start, we are going to release models for digits, commands and finally full transcription very soon. Keep watching :)
And this is just the start, we are going to release models for digits, commands and finally full transcription very soon. Keep watching :)
{
"config": {
"profanity_filter": false,
"encoding": "LINEAR16",
"speech_contexts": {"phrases":["yes","no"]},
"max_alternatives": 1,
"sample_rate_hertz": 8000/16000,
"language_code": "en-IN",
"enable_word_time_offsets": true
}
}