Findings of the 2023 ml-superb challenge: Pre-training and evaluation over more languages and beyond
The 2023 Multilingual Speech Universal Performance Benchmark (ML-SUPERB) Challenge
expands upon the acclaimed SUPERB framework, emphasizing self-supervised models in …
expands upon the acclaimed SUPERB framework, emphasizing self-supervised models in …
Development of a large spontaneous speech database of agglutinative Hungarian language
T Neuberger, D Gyarmathy, TE Gráczi… - Text, Speech and …, 2014 - Springer
In this paper, a large Hungarian spoken language database is introduced. This phonetically-
based multi-purpose database contains various types of spontaneous and read speech from …
based multi-purpose database contains various types of spontaneous and read speech from …
[PDF][PDF] Leveraging a Character, Word and Prosody Triplet for an ASR Error Robust and Agglutination Friendly Punctuation Approach.
Punctuating ASR transcript has received increasing attention recently, and well-performing
approaches were presented based on sequence-to-sequence modelling, exploiting textual …
approaches were presented based on sequence-to-sequence modelling, exploiting textual …
FMRI repetition suppression for voices is modulated by stimulus expectations
According to predictive coding models of sensory processing, stimulus expectations have a
profound effect on sensory cortical responses. This was supported by experimental results …
profound effect on sensory cortical responses. This was supported by experimental results …
AP16-OL7: A multilingual database for oriental languages and a language recognition baseline
We present the AP16-OL7 database which was released as the training and test data for the
oriental language recognition (OLR) challenge on APSIPA 2016. Based on the database, a …
oriental language recognition (OLR) challenge on APSIPA 2016. Based on the database, a …
The statistical signature of morphosyntax: A study of Hungarian and Italian infant-directed speech
J Gervain, RG Erra - Cognition, 2012 - Elsevier
Does statistical learning (Saffran, Aslin, & Newport, 1996) offer a universal segmentation
strategy for young language learners? Previous studies on large corpora of English and …
strategy for young language learners? Previous studies on large corpora of English and …
Ring that bell: A corpus and method for multimodal metaphor detection in videos
K Alnajjar, M Hämäläinen, S Zhang - arXiv preprint arXiv:2301.01134, 2022 - arxiv.org
We present the first openly available multimodal metaphor annotated corpus. The corpus
consists of videos including audio and subtitles that have been annotated by experts …
consists of videos including audio and subtitles that have been annotated by experts …
[PDF][PDF] Bulgarian Speech Corpora: A Review
D Dimitrova - Preprint. https://www. researchgate. net/publication …, 2023 - researchgate.net
This paper aims to provide a summary of the existing corpora of spoken Bulgarian. The
corpora are examined for their scope, genre, speech spontaneity, presence of phonetic …
corpora are examined for their scope, genre, speech spontaneity, presence of phonetic …
Word frequency cues word order in adults: cross-linguistic evidence
One universal feature of human languages is the division between grammatical functors and
content words. From a learnability point of view, functors might provide entry points or …
content words. From a learnability point of view, functors might provide entry points or …
Detecting English speech in the air traffic control voice communication
We launched a community platform for collecting the ATC speech world-wide in the ATCO2
project. Filtering out unseen non-English speech is one of the main components in the data …
project. Filtering out unseen non-English speech is one of the main components in the data …