Orsay - November 5, 2020Vocapia at Microsoft challenge on code-switched spoken language identification
As an R&D company, Vocapia research places high important on not only
following, understanding and actively contributing to the latest developments in
the speech processing field, but also networking and communicating with the
international community. One of our recent endeavors was our participation in
the first challenge and the ensuing First Workshop on Speech Technologies for
Code-switching in Multilingual Communities 2020, held (virtually) just after the
annual Code-switching in speech, the process of switching from one language to another in the same conversational sequence, is common in bilingual and multilingual communities and has been receiving growing attention in the speech and language communities. The language switch can be just the incorporation of words or short phrases from another language, or can be at a speaker turn or even larger level. The video of our workshop presentation describes our participation in the shared task challenge organized by Microsoft Research on language identification (LID) of code-switched speech in three language pairs: Gujarati-English, Telugu-English and Tamil-English. Vocapia, together with LIMSI-CNRS, have been developing and participating in evaluations of LID technologies for more than a decade. We have extensively explored a variety of approaches including phonotactic and acoustic ones, e.g. [Odyssey 2016] and [InterSpeech 2016]. LIMSI also addressed Code-Switching in French/Algerian Arabic Speech [Interspeech 2017]. Our submissions to the Microsoft challenge were ranked first in both LID tasks: the first (task A) detecting if a given utterance was monolingual or contained code-swithing; and the second (task B) ) producing a frame-level language labeling of code-switched speech. About Vocapia Research
Vocapia Research is a French R&D company and software publisher with over
20 years of experience in providing leading edge speech technologies for many
languages, including most major European languages as well as Arabic,
Mandarin, and Russian. The Vocapia Research VoxSigma® software
suite uses advanced language technologies such as language identification,
speech recognition, and speaker identification to transform raw audio and
audiovisual data into structured and searchable XML documents. This technology
relies on decades of research at LISN, with which there is a privileged
partnership. Joint systems developed with LISN have achieved top ranks in
national and international challenges on speech-to-text transcription. Located
at the heart of the science innovation cluster of Paris Saclay, France,
Vocapia Research is a leader in developing and adapting AI-based solutions for
both civil and defence applications. These applications include audio and
audiovisual data mining (broadcast and web data, telephone speech), production
of subtitles, OSINT and COMINT, and the analysis of aeronautical
communications (air traffic control, voice command). Readers who wish to get
more information about Vocapia Research are invited to check out the Vocapia
Research website or use the contact information
page http://www.vocapia.com/contact.
|
