ALBAYZÍN EVALUATIONS
IBERSPEECH-RTVE 2022 CHALLENGE RESULTS

DATASETS

The organization released a corpus consisting of more than 700 hours of TV shows from Radio Televisión Española (RTVE), more than 80 hours of speech from 3/24 TV channel (Corporació Catalana de Mitjans Audiovisuals, CCMA) and more than 20 hours of speech from Aragón Radio (Corporación Aragonesa de Radio y Televisión, CARTV).
RTVE Databases License
    The RTVE data is available subject to the terms of a licence agreement with the RTVE.
    To download the RTVE databases,  a representative of your research group, company,..., must sign the license agreement (Digital signature is valid)
3/24 TV channel and Aragón Radio Databases

Please contant the challenge organizers

SYSTEM DESCRIPTIONS

CHALLENGE RESULTS PRESENTATION

SPEECH to TEXT CHALLENGE (S2TC)

The Speech to Text Challenge (S2TC) consists of automatically transcribe different types of TV shows. More information and evaluation plans ...

SPEAKER DIARIZATION and IDENTITY ASIGNEMENT(SDIAC)

The Speaker Diarization and Identity Asignement (SDIAC) consists of segmenting broadcast audio documents according to different speakers, linking those segments which originate from the same speaker and identify a closed set of speakers. More information and evaluation plans ...

SPEAKER DIARIZATION
Speaker Diarization
SPEAKER DIARIZATION and IDENTITY ASIGNEMENT
Speaker Diariation and Identity Asignement

TEXT AND SPEECH ALIGNMENT CHALLENGE (TASAC-ST)

(Task 1)TaSAC-ST:Alignment of respeaking generated subtitles, organized by RTVE and Universidad de Zaragoza, consists of synchronazing the broadcast subtitles created by respeaking of different TV shows.
More information and evaluation plans ...