We are very proud of the questfox development in speech. It is possible to record someones voice and to transcribe what the person said into text.
With more than 120 languages integrated, we are perhaps the leading tool for this kind of feature in market research.
As more and more users were saving thousands of answers on our servers we constantly discussed this feature set for security and performance reasons.
Saving Audio and Video Files outside of questfox
The idea of questfox speech tools is to receive the content said as a transcribed text. On top of this procedure questfox allows to save the recorded voices. The default setting for recording audio is OFF. So you need to switch ON this feature if you want to use it and later listen to the audio files.
To record the audio files you can switch the answer settings of an audio question type to ON.
The multimedia files used to be saved independently from the answers on the questfox server in a special folder structure.
In this setting we could not prevent that project admins of a project space could listen to the audios of other projects in the same project space.
In projects with thousands of audio files we had to admit, that performance of data handling in gigabytes became an issue in the browser. With the new approach this is over. You can decide where to save your data and you will have much quicker access as you can use your established tools to work with these multimedia files.
Security by Design with SFTP
Multimedia Files are now saved on the client’s side via SFTP
We now changed this forever and fulfill an important demand of our clients who always ask: Where is the data stored? From now on the answer will always be the same: The multimedia files are saved in your own security environment and not be in connection with the rest of the survey.
The recorded answer can be saved in your own environment and therefore out of everyone’s reach, using questfox. This is a major improvement in the field of data security as the multimedia data is now stored on the client’s side.
Important Notice: Make sure, that you have a user’s allowance to record his or her voice or video before saving this very personal information somewhere on the internet. This was a requirement before this new technology was implemented and still needs to be respected.
questfox is not responsible for your behavior and not reliable for your actions with our software. So please take data protection issues serious – especially in this very delicate field.
How to integrate your SFTP Server into questfox
Under CREATE – Projects Settings you will find a place to integrate your SFTP Settings.
Your password will never show-up in questfox and cannot be copied from the data input file.
When pressing the Connection Test button you should receive the following message when all input data is correct.
questfox settings for optional audio recording on your own SFTP Server
Organize your data following your needs
The data can be organized by three different settings: Question, Calendar Week or Participant. We advise you to do this only once per project to avoid confusion in the data structure.
Default is the organisation by question. Saving a single file would create a folder called “questfox” on your SFTP Server with a subfolder carrying the project ID and more subfolders named Q1 .. Qn with your multimedia data.
If you wish to organize the folder structure differently you can switch to “Order by Calender Week” and see the result later as “44-2020” which is the 44th week of the year 2020.
If you plan to look at the answers of one person you can organize the folder structure by “Participant”. questfox would create one folder for each individual and ad the answers to one question in this folder organized by question number (here Q1 and Q2).
And by the way: We updated to the most recent versions of transcription services. So the overall quality should become always better.
We wish you all the best with this new security feature which gives you the full power to manage sensitive data on your side. The flexibility of this approach will be important for complex projects.
FLAC – Free Lossless Audio Codec
In order to be independent from any kind of manufacturer we opted for the FLAC Codec to save in perfect nearly lossless quality.
For understanding this codec better we recommend this link https://en.wikipedia.org/wiki/FLAC
In case your Audio-Tool is not able to play this data we recommend the VNC Player which can be used entirely free of charge. Download available here: https://en.vlc.de/
OOV – Out of vocabulary – questfox is sometimes leaving us speechless.
Week by week we see incredible advances in the development of our speech-to-text approach inside of questfox. One of the everlasting challenges is the wrong transcription of words which are not correctly understood in a specific context.
If something is misspelled by a computer this normally happens when the word used is outside the standard vocabulary of the application. This tends to happen often when words are used in a company specific context. By the way this seems to be true for every single market research project.
When asking about a brand some may be asking for competitors with a very special name and a very special spelling. In these cases the transcription technology tends to fail to recognize those specific names. Technically speaking the words used are “out of vocabulary” (OOV).
The questfox solution to the OOV problem: It is now possible to create a list of special words to be integrated in questfox. Everytime the transcription engine of questfox is used this list is sent to the transcription engine to have a better understanding of specific vocabulary used.
Here is our questfox experiment to test the tool with some less common brands
|Brand||Transcription without OOV List||Transcription with OOV List|
|pangea labs||Pangea Labs||pangea LabsPangea Labs|
|Wisdom of Krauts||wisdom of crowds||wisdom of crowds|
|Tjaereborg Reisen||Sherlock Reisen|
|Comme des Garçons||komm DKVkomm digga Song||comme de garcon Gasthaus.com Digger|
kommen die ganzen
As you can see the overall transcription results do improve. But some issues remain.
Those who use mixed spoken language inside one dictation process may be familiar with the fact that transcription only works for one language at a time and hardly ever for two languages simultaneously.
As questfox works with an “expected language” tag for the transcription everything which is far away from the expected language is difficult to understand by the tool. In our pretest language German it was not possible to capture the french brand “Comme des Garçons”. We also failed with our made up brand “Wisdom of Krauts” which is still not transcripted in the desired way. The correct spelling seems to dominate the process and we get the undesired transcription result even after putting it into the list of special words. 😦
The only questfox way to “correct” this spelling would be the use of Regular Expressions in the questlogix. By the way: questlogix is such a distinct word with no similarity in the dictionary that our integration in the list of special words did function right away. Here is how to use RegEx in questfox:
Even while still in development we hope that you appreciate the publication of this feature and share your experience with us.
At first we defined the usage based on each questfox project as we believe that every specific project might have the same vocabulary issues inside one project. You can define your individual “Bag of Words” in the projects settings
The syntax is separate each word by comma. If you have several words just use them in a row
Word, word, word, combination of words,
Our typical list would be
questfox, pangea labs, questlogix, what’s your quest?, Speech2Text
In questfox you can paste one list of words per project under
-> Special List of Words for Transcription / Out of Vocabulary (OOV)
Please share your gained knowledge about this feature.