Page MenuHomePhabricator

Cyrta (Pawel Cyrta)
User

Projects

User does not belong to any projects.

Today

  • Clear sailing ahead.

Tomorrow

  • Clear sailing ahead.

Tuesday

  • Clear sailing ahead.

User Details

User Since
Nov 24 2016, 4:00 PM (286 w, 2 d)
Availability
Available
LDAP User
Unknown
MediaWiki User
Cyrta [ Global Accounts ]

Recent Activity

Sep 6 2018

Cyrta added a comment to T176002: Create updated contract about Monumental.

What is the contract for me about Monumental ?

Sep 6 2018, 3:09 PM · Connected-Open-Heritage, User-Jopparn

Dec 16 2016

Cyrta added a comment to T122188: [Story] Recording of shorter texts (Wikispeech).

There is no task related to "promptest" creation.
Where is listing of utterances to be recorded ?

Dec 16 2016, 1:27 PM · Story, Wikispeech, Wikispeech-Recording
Cyrta added a comment to T122156: [Story] Recording API (Wikispeech).

There is very good software already available for both TTS and ASR recording

Dec 16 2016, 1:25 PM · Story, Wikispeech, Wikispeech-API, Wikispeech-Recording, Wikispeech-Synthesis
Cyrta added a comment to T151880: Caching on TTS server.

Yes, but also the "page" is going to indicate language but not voice,

  • language
  • voice
  • utterance

That could be sufficient. And maybe:

  • page
  • text coordinates on page

Simple Redis, Memcached could be used to store indexes and paths to the files.

Dec 16 2016, 1:18 PM · Wikispeech-Jobrunner, Wikispeech-Text-to-Speech
Cyrta added a comment to T151880: Caching on TTS server.

using simple key-value store, we can cache responses on server side too,
TTS result would be store in file and indexed according to the page and text coordinates + utterance itself.

Dec 16 2016, 12:58 PM · Wikispeech-Jobrunner, Wikispeech-Text-to-Speech

Dec 9 2016

Jopparn awarded T133893: [Task] Development of the lexicon through simple tools (Wikispeech) a Like token.
Dec 9 2016, 4:09 PM · Wikispeech-WMSE, Wikispeech, Wikispeech-Lexicon, Wikispeech-NewLanguages

Nov 24 2016

Cyrta added a comment to T133893: [Task] Development of the lexicon through simple tools (Wikispeech).

I think we can write to prof. Tanja Schulz and ask if she can give us access to this RTAL tool.
In every paper it is stated it is free tool.

Nov 24 2016, 4:33 PM · Wikispeech-WMSE, Wikispeech, Wikispeech-Lexicon, Wikispeech-NewLanguages
Cyrta added a comment to T133893: [Task] Development of the lexicon through simple tools (Wikispeech).

in " web-based tools and methods for rapid pronunciation dictionary creation "

As shown in Fig. 2 Wiktionary pages may contain more than one pronunciation per word. These additional pro- nunciations reflect alternate pronunciations, dialects or even different languages. To gain some insights into this “language-mix” we performed a brief analysis on the Eng- lish, French, German, and Spanish Wiktionary editions. For German Wiktionary, for example, we found that only 67% of the detected pronunciations are for German words, the remainder is for the languages Polish (10%), French (9%), English (3%), Czech (2%), Italian (2%), etc. Fig. 3 shows this “language-mix” in the English and the French editions.

Nov 24 2016, 4:29 PM · Wikispeech-WMSE, Wikispeech, Wikispeech-Lexicon, Wikispeech-NewLanguages
Cyrta added a comment to T133893: [Task] Development of the lexicon through simple tools (Wikispeech).

There were tools for that to crawl wikipedia or get data from expedia
made by team of Tanja Schulz from Institute for Anthropomatics, Cognitive Systems Lab (CSL), Karlsruhe Institute of Technology (KIT),

Nov 24 2016, 4:27 PM · Wikispeech-WMSE, Wikispeech, Wikispeech-Lexicon, Wikispeech-NewLanguages