Posts Tagged ‘video’

German speech model ‘friedrich’

Friday, February 18th, 2011

You can import the German speech model 'friedrich' (0.5 MB, GPLv3) into simon. The package contains all necessary files: hmmdefs-friedrich, tiedlist-friedrich, macros-friedrich, stats-friedrich, and of course the scenario-file scenario-friedrich.xml.

Edit: Download the video German speech model ‘friedrich’ (40 min., 47 MB, WMV, link will become invalid soon)

Edit: These words are recognized in the video:

ARBEITSAUFNAHME Aachener Rachens Einsparens Aalen Racheschach RAF
Abarbeiten Barockzeit Abarbeitungszyklus Abartung Abbauvermgen
Abbauvertrag Abberufens Abberufungen Abbestellungen Abbiegevorgang
Abbiegevorgangs Abbiegevorgnge Abbiegevorgngen Abbindebehandlung
Abbindebereich Abbindebeschleuniger Abbindebeschleunigung Abbindedauer
Abbitte Abbindung Abbindezeit Abbindewasser Abbindeverhalten (more…)

Creating Ralf’s German dictionary

Tuesday, September 22nd, 2009

To get an impression how I create the German PLS dictionary, watch the video (19.2 MB, WMV):

[20100101: video removed]

Currently, I am preparing a new version of Ralf’s German dictionary. The dictionary should be 100% simon compatible (version 0.1 contains some minor mistakes).

This is what I did yesterday:
1. I created more than 80.000 pronunciations with eSpeak from a set of 300.000 words. Not all words were transcribed, I don’t know what went wrong.
2. Then I created an XSLT stylesheet to transform the eSpeak phoneset into IPA with saxonb-xslt.
3. The result was that I had a list of the phonemes, but the graphemes are missing. What can I do? I decided to start dictating the missing graphemes with DNS 9.5. You can see the dictation process in the video.

148 words out of 158 recognized correctly

Thursday, July 23rd, 2009

I just videotaped all words that are contained in my active lexicon. You can see in the video …

Dictation under Ubuntu: 148 German words recognized correctly (32 MB, WMV, 12:58 minutes)

… how I dictate the following words (words that were recognized wrong are marked with an asterisk):

abnahmen Computer das Entfernung Entstehungen Ereignis Erlebnissen Gründern* Europas Globalisierung* extrem Fahrrads Fahrzeugen Fallen falsch Fausts Februar Feinden Fernsehers festgestellt Feuerwehr Finanzamts Finnlands Flaschen Fleischer Flugzeugen folgen Forschungen Fortschritten Fraktionen Frankfurtern Frankreichs Freiheiten Freitagen Friedhöfen Funktionen Fusionen Fußbällen Fußgängern Fähigkeiten Gaststätten gebaut gebildet gebildetem Geburtstagen Gedichten Gefängnissen Gegensatzes Gegenstands Gegenwart Geheimdiensten Geheimnissen Telefons* Gehältern Geistern Geldern gemeinsam Gemälden Genehmigungen Finnlands* Gerechtigkeit Gerichte geringem Geschenken Geschichten Geschmacks Geschwindigkeiten Geschäften Gesellschaften Gesetzgebers Gesichtern schlecht* Gestalten Gesundheit Gewichten Gewinnern Gewässern Globalisierung Grabes Gramms Grenzen Großmutter Großvater Grundgesetz Grundschulen Grundstücken Gräbern Gründern Gymnasiums Gänge Gärtner Gästen Göttern Haaren Hafens Hamburgern Handlung Handwerker Hannovers Hauptbahnhof Hauptstadt Haus Haushalten Heimat Herbst Flaschen* Herzog Hessens Gemälden* Hochzeiten Hoffnungen Horizonten Hubschraubern Hunger Häfen Hälften Höfen Identitäten Illusionen Indonesiens Informationen Initiativen Instrumenten ist Jahrhundert Kalifornien Transport* Geistern* Management natürlich neu neue niedrigem offiziell optimistisch organisiert positives Produkt Professor Schauspieler schlecht sehr Sicherheit Silvester Sonntag Technologie Telefons Termine Thailands Fahrzeugen* Transport unterhielt Wetter worden zeichnet Zeile Zuschauer Zweifel

I dictated all 158 words from the lexicon. The average length of each word is about 10 characters (it would be interesting to know: what is the average phoneme length?). I choose words that are mostly not too short to get a better recognition result.

How many of the words were recognized wrong? I have to count the asterisks (*). I counted ten asterisks. That means: 148 words out of 158 were recognized correctly. Or about 93 % of the dictated words were recognized correctly.

I think that from now on, 93 % recognition rate should be the lower bound. I hope that the recognition rate doesn’t drop when I add more words to the active vocabulary.

What will I have to do? I will take a closer look at the triphones. You want to know how they look like? Just open the file wintri.mlf e.g. with Notepad++.

Video: I just recorded about 77 words

Monday, July 20th, 2009

I just recorded about 77 words. Most of them were recognized correctly (about 72 words). Some were recognized wrongly (about 5 words). The wrongly recognized are marked with an asterisk (*):

Geheimnissen Gehirns Geistern Geldern gemeinsam Genehmigungen Gerechtigkeit Gerichte geringem Geschichten Geschmacks Geschenken Generals Geschwindigkeiten Gewässern Gewinnern Gesetzgebers Geschäften Globalisierung Gestalten Gesprächen Glücks Großmutter Großvater Grundgesetz Grundschulen Gründern Gräbern Gymnasiums Gänge Gärtner Gästen Haaren Hafens Hamburgern Handlung Handwerker Hannovers Hauptbahnhof Hauptstadt Haushalten Heimat Herbst Hessens Herstellung Herzog Himmel Hochzeiten Hoffnungen Horizonten Hubschraubern Hunger Hälften Höfen Indonesiens Initiativen Instrumenten Jahrhundert Kalifornien Geistern* Erdbeben* niedrigem Fußbällen* optimistisch organisiert positives Professor Schauspieler Distanz* Technik Technologie Therapien Transport Grundschulen* zeichnet Zuschauer Zweifel

The lexicon contains about 159 entries (I didn’t dictate all of the entries). Maybe I should dictate all of them in a row, and publish a video about the result?

About 93 % of the words were recognized correctly.

And now, watch the video Dictating more than 70 words under Ubuntu (17.6 MB, 7:10 min).

Video: dictating under Ubuntu

Saturday, July 18th, 2009

I have uploaded a video with the title Dictating with simon 0.2 under Ubuntu (7.8 MB; 3:10 min.). The video shows how I dictate 45 German words with simon. It is similar to the previous one.

Most of the words dictated in the video can be found in the German PLS dictionary, too.

Video: dictating German words

Friday, July 17th, 2009

I have prepared a small video (6.8 MB, 2.51 min.) which shows how I dictate about 40 German words with simon 0.2. You will see that it works pretty well, and speech recognition under Ubuntu is possible. There is only one recognition error in the video.