Spontaneous speech contains a significant amount of disfluencies and non-lexical sounds
(eg, backchannels, filled pauses), which are often difficult to transcribe. Disfluency labeling …

Automatic speech recognition systems based on self-supervised learning yield excellent
performance for read, but not so for conversational speech. This paper contributes insights …

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 …

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 …

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 …

This paper presents a Benchmark Intended Grouping of Open Speech (BIGOS), a new
corpus designed for Polish Automatic Speech Recognition (ASR) systems. This initial …

This study outlines our duration-dependent modeling experiments on limited-resource
Hungarian speech recognition tasks. As it is well known, very short utterances pose …

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 …

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 …

Shared tasks or challenges provide valuable opportunities for the machine learning
community, as they offer a chance to compare the performance of machine learning …