ILA - teachable voice assistant Files

ILA development files require the full version of ILA, please visit the GitHub repository for all legacy files:

ILA GitHub page: https://github.com/fquirin/ILA

For the dev files please download: https://sourceforge.net/projects/ila-voice-assistant/files/ILA_Beta_v3.8_Dev_Files.zip/download


SEPIA Framework - ILA successor
---------------------------------

ILA has not been changed since v3.8 back in 2016, but there is a new member in the family called SEPIA, check it out: https://sepia-framework.github.io/
SEPIA carries on the tradition of ILA but has a completely new architecture containing a server and a client-app.


ILA BETA v3.8 - getting more context!
---------------------------------------

Hello everybody! It's been a while since the last update but finally here it is: ILA Beta v3.8! :-)

The most obvious first, ILA got some fresh new look ^^. Hope you like it! (if not don't worry you can always go back to classic). The more subtle changes are various improvements in the Add-ons and finally ILA got some context ... I mean commands that depend on context :-) Here is a more detailed patch list:

- New looks for ILA: 4 new skins to choose from plus the classic look.

- Context dependent commands that can be reused. An example: imagine you'd say "open the third" ... could be useful in many situations right, so now you can define it multiple times. See the tutorial on the homepage for a detailed description about contexts.

- Besides the normal context, there is also a super-context. Commands defined with this parameter will only work in a certain environment that you can activate before (imagine you'd switch from your smart home to your smart car, same commands will probably trigger different actions).

- Add-ons have been improved and support 'open parameter' commands like every other command of ILA (see teaching tutorial on the homepage if you don't know what I mean :-) ) and it is possible now to load answers from an external file including support for languages and parameters.

- 'Open parameters' work with custom answer/conversation commands now as well, you just have to add 2 brackets at the end, e.g. use 'do you like ()' and define a couple of answers and ILA will answer everything like "do you like movies", "do you like ice cream" ... with these random answers.

- Word and letter error thresholds used to do the auto-correction/adaption of unknown commands can be set in the config.properties now. Increasing the values would make unknown commands more likely to get accepted when compared to known ones, but be careful sometimes a little word like 'not' can change the meaning of a sentence completely ;-)

- As usual there are many bugs fixed and some tweaks done to the UI (e.g.: skipping and aborting stuff is more reliable now).

- Oh and before I forget, I've added the first (very rough and basic) version of an XBMC/Kodi voice remote add-on, feel free to improve it ^^

Hope you like it! (context: the update) ;-)
- Florian


ILA BETA v3.7 - a lot more freedom :-)
---------------------------------------

For a while now ILA works pretty reliable using the Sphinx-4 (offline) engine to recognize speech. This works mainly by restricting the vocabulary to obtain good recognition results. Restriction means a working system in this case ... but let's face it: we want FREEDOM! because fun comes with a large vocabulary :-) Up till now Google was able to give us this freedom but it required an API key (complicated to get) and came with restrictions of usage :-( ... so no real freedom. But thanks to the wonderful web API of Google and a nice technique called websockets we are finally free of restrictions now! Of cause that also means Google is free to gather more information on us while we use their services! =)
Besides freedom ILA beta 3.7 comes with a hand full of other neat features, here is the (approx.) complete list:

- Google is back! Full implementation of a new recognizer using Google's web speech API. To get this thing running please see the tutorial (basically you just need to install Chrome or Chromium browser)

- The add-on (plug-in) system of ILA has been reworked introducing more freedom (again ^^) and accessibility in designing add-ons. Add-ons are now completely independent classes and the commands they supply are auto-loaded into ILA's teachGUI. You only have to make one basic class implementing the ILA_addon_interface and the rest is up to you. For more details watch out for a new tutorial and have a look at the new developer version 3.7.

- Freedom is the word of the day ^^ so why not write your own speech recognizer or synthesizer for ILA using one of the two new classes 'STT_CustomRecognizer' and 'TTS_CustomSynthesizer'.

- Handling processes has been greatly improved especially for Linux systems giving you a) the freedom(!) to choose a program to open apps/files and b) keeping track of multiple processes in preparation of advanced opening and closing commands (updates will follow e.g.: "ILA, open my music player", "ILA, close my music player"). See the 'Apps' folder for more details!

- Approximate matching of input (speech and commands) has been improved to check not only for wrong words ('approxSearchErrorRateThresh') but also for letters. Watch out for the new 'approxSearchLetterErrorsThresh=3' in the config.properties file (3 means if we have less than 4 wrong letters compared to a saved command it's still recognized).

- Individual browser calls can be deactivated now by removing (or commenting out) links from 'ILA/Data/linkList_xy.txt' file. Why do we want to do this? Because we want to have the freedom(^^) to decide if the browser opens when asked for the weather for example.

- In case you notice a feedback of the confirmation blib-sound in your recordings (rec.wav) you can add a delay to the recording. Check '/Data/config.properties' for 'recordingDelay=0' (given in miliseconds).

- Removed some bugs like broken UTF-8 encoding in ILA's memory files, failed overwriting of double commands while teaching and minor stuff regarding weather, processes, dates/reminders and more.

Hope you like the new freedom ;-)
- Florian


ILA BETA v3.65 - smaller update with bug fixes
-----------------------------------------------

I quickly updated ILA to fix some bugs in the new reminder system. Besides that I added 2 new classes so one can better adapt ILA to new languages and new speech engines (custom_interpreter & custom_recognizer). Some other minor tweaks include:
- mllr auto-loading for Pocketsphinx (filename must be: mllr_matrix)
- possibility to deactivate browser calls (e.g.: I noticed that I rarely look at the screen when asking ILA for the weather, so now you can simply comment out the corresponding line in linkList.txt to avoid the browser to open, use // to comment).
- added the two commands "I'm leaving" and "I'm back" to trigger the associated reminders
- added a new option to "config.properties": recordingDelay=0 (in ms) because I noticed that sometimes the blib-sound of ILA could be heared in the recording (it seems to be a delayed feedback when microphone and speakers are not the same device). If you experience problems like that try adding a dealy of 100-200ms


ILA BETA v3.6 - major update
-----------------------------

ILA has been updated with full Pocketsphinx support (including keyphrase spotting), more complex reminders, more options for contacts an upgraded ILA-personality, performance improvements due to smarter resource allocation and much more. Details will follow soon!
Downloads on Sourceforge have been temporary disabled, please visit ILA's homepage for all files:

https://sites.google.com/site/ilavoiceassistant/downloads


ILA BETA v3.5 - fixes for Linux
--------------------------------

I noticed some nasty bugs in the Linux (Ubuntu 14.04) version of ILA mainly coming from conflicts between Minim, Java an PulseAudio. In the worst case
ILA could not speak anymore or was crashing a lot. I fixed what I could but if you still have problems I strongly recommend to install the latest Oracle
Java 8. Together with the bug fixing I've also included some new features :-)

- Integration of Pocketsphinx command line tool to better support low performance systems. You need to have Pocketsphinx installed (Linux) or put a pre compiled version (Win) in the subfolder SpeechData/Pocketsphinx (a Win8 version is included) to use it. Unfortunately I couldn't get the keyphrase spotter running yet. There is a config file for Pocketsphinx too in case you want to add parameters (SpeechData/default.pocketsphinx.config) (see pocketsphinx tutorial)
- Added grammar/non-grammar switching for pocketsphinx too and improved it to work better in combination with 'hey ILA' (if you've deactivated grammar restrictions completely)
- I've completely rewritten the 3rd layer of input analysis (1st is check of teachIt memory-file, 2nd is keyword isolation). If the 1st and 2nd layer fail ILA will try to do an approximate match to the language-knowledge-base that means everything inside teachIt.txt and languageModelBase.txt. The approximate match is done with (kind of) an edit-distance. The threshold for an approximate match can be set in the config file (Data/config.properties -> approxSearchErrorRateThresh (basically WER))
- For people experimenting with 'addons' there is a new method "ILA_speechControl.askDirectQuestion("whaaaat?");" that can be used to let ILA ask direct questions from anywhere inside the code. The answer is obtained by checking ILA.lastInput. Check the 'batchaccuracytest' addon for an example.

Thats it for now. Hope you enjoy :-)
- Florian

ILA BETA v3.4:
--------------

Hello everybody,

just a few days after the release of Beta v3.3 I'm happy to present you v3.4 already :-) I needed to fix some bugs and took the chance to include a bunch of improvements too!
Here is the (almost) complete list of changes:

- fixed the timeout bug in the system 'test' command and made it a bit more fancy :-)
- added the contacts list to the automatic creation of the dynamic language model (dlm) (yes! there is a contacts.txt list ^^)
- removed any numbers from 'App'-names during auto loading into the dlm, ILA is not very flexible with number-to-string conversion yet :-(
- added the possibility to correct (delete) what you have said by saying "I repeat" (de: ich wiederhole) or "I said" (de: ich sagte) followed by a short pause. So when you know you messed up an input just say "-pause- 'I repeat' -pause-" :-) This works especially nice in the Live-mode! (only Sphinx-4)
- added some more ILA comments when the program needs to reload stuff so you know now that you have to wait a bit ;-)
- added some tooltips to settings (especially for the selection of the default recognizer)
- finally fixed saving and loading of the speaker adaptation data for good (it works reliable now with all tested models)
- added the PTM 8kHz acoustic model to the default set of models. I recommend to try this one if your accuracy is rather low. To use it please adjust the 'acoustic model' in settings.
- auto-loading the sample rate of the acoustic models by placing a 'samplerate.properties'-file inside the folder of the AM (see included models)
- added a 'test accuracy' command to test again the accuracy of the recorded speech in Data\test.wav (created during speaker adaptation)
- added a 'batch test' command as an addon to test a bunch of .wav-files recorded and saved with transcription. You can use the 'amt' (acoustic model training) command to record these files
- ILA saves the speech recorded during the system test ('test') now and uses that to initialize the recognizer (usually the first sentences where always crap somehow oO ^^)
- included updates in Sphinx-4 (LiveCMN and BatchCMN improves the recognizer? small case dictionary)
- completely rewrote the Google speech recognition part to get rid of old bugs and dependencies and removed the old API
- more bug fixing

I've also uploaded a 'developer version' of ILA that comes with less 'extras' like different acoustic models but with some source code to let you develop add-ons or adapt the language files.
Check out 'ILA_Beta_v3.4_DeveloperVersion' package :-) I'll add more code over time.

For more info and tutorials check out ILA's homepage: https://sites.google.com/site/ilavoiceassistant/
If you have any questions or want to share your project please post here: https://sourceforge.net/p/ila-voice-assistant/discussion/

Have fun!
Florian