[PDF][PDF] On Disfluency and Non-lexical Sound Labeling for End-to-end Automatic Speech Recognition
Spontaneous speech contains a significant amount of disfluencies and non-lexical sounds
(eg, backchannels, filled pauses), which are often difficult to transcribe. Disfluency labeling …
(eg, backchannels, filled pauses), which are often difficult to transcribe. Disfluency labeling …
[PDF][PDF] What do self-supervised speech representations encode? an analysis of languages, varieties, speaking styles and speakers
J Linke, MS Kádár, G Dobsinszki, P Mihajlik… - InterSpeech2023 …, 2023 - isca-archive.org
Automatic speech recognition systems based on self-supervised learning yield excellent
performance for read, but not so for conversational speech. This paper contributes insights …
performance for read, but not so for conversational speech. This paper contributes insights …
Narrowing or in Kálmán's writings: Investigating the usage of vagy 'or' in Hungarian
A Viszket, E Kárpáti, J Kleiber - Acta Linguistica Academica, 2024 - akjournals.com
The paper investigates the usage of the Hungarian connective vagy 'or'. Our starting point is
Ariel & Mauri's (2018, 2019) and Ariel's (2020) papers about the use of or, where they argue …
Ariel & Mauri's (2018, 2019) and Ariel's (2020) papers about the use of or, where they argue …
A survey of Polish ASR speech datasets
M Junczyk - Poznan Studies in Contemporary Linguistics, 2024 - degruyter.com
Access to speech datasets is essential for the effective use of modern ASR systems in low-
resource languages like Polish. However, the lack of centralized information and metadata …
resource languages like Polish. However, the lack of centralized information and metadata …
Is Spoken Hungarian Low-resource?: A Quantitative Survey of Hungarian Speech Data Sets
Even though various speech data sets are available in Hungarian, there is a lack of a
general overview about their types and sizes. To fill in this gap, we provide a survey of …
general overview about their types and sizes. To fill in this gap, we provide a survey of …
BIGOS-Benchmark Intended Grouping of Open Speech Corpora for Polish Automatic Speech Recognition
M Junczyk - 2023 18th Conference on Computer Science and …, 2023 - ieeexplore.ieee.org
This paper presents a Benchmark Intended Grouping of Open Speech (BIGOS), a new
corpus designed for Polish Automatic Speech Recognition (ASR) systems. This initial …
corpus designed for Polish Automatic Speech Recognition (ASR) systems. This initial …
Tandem Long-Short Duration-based Modeling for Automatic Speech Recognition
This study outlines our duration-dependent modeling experiments on limited-resource
Hungarian speech recognition tasks. As it is well known, very short utterances pose …
Hungarian speech recognition tasks. As it is well known, very short utterances pose …
Narrowing or in Kálmán's writings
A VISZKET, E KÁRPÁTI, J KLEIBER - 2024 - ceeol.com
The paper investigates the usage of the Hungarian connective vagy 'or'. Our starting point is
Ariel & Mauri's (2018, 2019) and Ariel's (2020) papers about the use of or, where they argue …
Ariel & Mauri's (2018, 2019) and Ariel's (2020) papers about the use of or, where they argue …
[PDF][PDF] What kind of multi-or cross-lingual pre-training is the most effective for a spontaneous, less-resourced ASR task?
P Mihajlik, MS Kádár, G Dobsinszki… - 2nd Annual Meeting …, 2023 - sigul-2023.ilc.cnr.it
Most languages are under-resourced for Automatic Speech Recognition (ASR), and most
relevant tasks are related to the transcription of spontaneous speech. The application of …
relevant tasks are related to the transcription of spontaneous speech. The application of …
[PDF][PDF] Combining Acoustic Feature Sets for Detecting Mild Cognitive Impairment in the Interspeech'24 TAUKADIAL Challenge
G Gosztolya, L Tóth - isca-archive.org
Shared tasks or challenges provide valuable opportunities for the machine learning
community, as they offer a chance to compare the performance of machine learning …
community, as they offer a chance to compare the performance of machine learning …