6 |
PRONOMBRES DE FORMA: EL USO ANAFÓRICO DE MARCAS DE CLASE EN MIRAÑA
|
|
|
|
In: Forma y Función, Vol 22, Iss 1, Pp 67-94 (2009) (2009)
|
|
BASE
|
|
Show details
|
|
7 |
PRONOMBRES DE FORMA: EL USO ANAFÓRICO DE MARCAS DE CLASE EN MIRAÑA
|
|
|
|
In: Forma y Función, Vol 22, Iss 1, Pp 67-94 (2009) (2009)
|
|
BASE
|
|
Show details
|
|
8 |
Pronombres de forma: el uso anafórico de marcas de clase en Miraña
|
|
|
|
In: Forma y Función, Vol 22, Iss 1 (2009) (2009)
|
|
BASE
|
|
Show details
|
|
9 |
PRONOMBRES DE FORMA: EL USO ANAFÓRICO DE MARCAS DE CLASE EN MIRAÑA FORMAL PRONOUNS: THE ANAPHORIC USES OF CLASS MARKERS IN THE MIRAÑA LANGUAGE
|
|
|
|
In: Forma y Función, Vol 22, Iss 1, Pp 67-94 (2009) (2009)
|
|
BASE
|
|
Show details
|
|
12 |
Motivos para la documentación de lenguas en vías de extinción
|
|
|
|
In: Forma y Función, Iss 13 (2000) (2000)
|
|
BASE
|
|
Show details
|
|
13 |
Untrained Forced Alignment of Transcriptions and Audio for Language Documentation Corpora using WebMAUS
|
|
|
|
In: http://www.lrec-conf.org/proceedings/lrec2014/pdf/1176_Paper.pdf
|
|
Abstract:
Language documentation projects supported by recent funding intiatives have created a large number of multimedia corpora of typologically diverse languages. Most of these corpora provide a manual alignment of transcription and audio data at the level of larger units, such as sentences or intonation units. Their usefulness both for corpus-linguistic and psycholinguistic research and for the development of tools and teaching materials could, however, be increased by achieving a more fine-grained alignment of transcription and audio at the word or even phoneme level. Since most language documentation corpora contain data on small languages, there usually do not exist any speech recognizers or acoustic models specifically trained on these languages. We therefore investigate the feasibility of untrained forced alignment for such corpora. We report on an evaluation of the tool (Web)MAUS (Kisler et al., 2012) on several language documentation corpora and discuss practical issues in the application of forced alignment. Our evaluation shows that (Web)MAUS with its existing acoustic models combined with simple grapheme-to-phoneme conversion can be successfully used for word-level forced alignment of a diverse set of languages without additional training, especially if a manual prealignment of larger annotation units is already avaible.
|
|
Keyword:
forced alignment; language documentation corpora; word times
|
|
URL: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.423 http://www.lrec-conf.org/proceedings/lrec2014/pdf/1176_Paper.pdf
|
|
BASE
|
|
Hide details
|
|
14 |
REPic16 ; Picture 16 of ShaClaTa, Roberto (Pi'mui) and Ernesto (Jo'mai)
|
|
Frank Seifart. - : The Language Archive, Max Planck Institute for Psycholinguistics
|
|
BASE
|
|
Show details
|
|
16 |
RGPic14 ; Picture 14 of ShaClaTa, Rafael (Boita) and Gregorio
|
|
Frank Seifart. - : The Language Archive, Max Planck Institute for Psycholinguistics
|
|
BASE
|
|
Show details
|
|
19 |
REPic08 ; Picture 8 of ShaClaTa, Roberto (Pi'mui) and Ernesto (Jo'mai)
|
|
Frank Seifart. - : The Language Archive, Max Planck Institute for Psycholinguistics
|
|
BASE
|
|
Show details
|
|
20 |
AGPic12 ; Picture 12 ShaClaTa, Andrea and Gloria
|
|
Frank Seifart. - : The Language Archive, Max Planck Institute for Psycholinguistics
|
|
BASE
|
|
Show details
|
|
|
|