Related papers: Tusom2021: A Phonetically Transcribed Speech Datas…
Training automatic speech recognition (ASR) systems requires large amounts of data in the target language in order to achieve good performance. Whereas large training corpora are readily available for languages like English, there exists a…
Ramsa is a developing 41-hour speech corpus of Emirati Arabic designed to support sociolinguistic research and low-resource language technologies. It contains recordings from structured interviews with native speakers and episodes from…
Since 2022 we have been exploring application areas and technologies in which Artificial Intelligence (AI) and modern Natural Language Processing (NLP), such as Large Language Models (LLMs), can be employed to foster the usage and…
Automatic Speech Recognition (ASR) has increasing utility in the modern world. There are a many ASR models available for languages with large amounts of training data like English. However, low-resource languages are poorly represented. In…
Automatic speech recognition for low-resource languages remains fundamentally constrained by the scarcity of labeled data and computational resources required by state-of-the-art models. We present a systematic investigation into…
Speech processing systems rely on robust feature extraction to handle phonetic and semantic variations found in natural language. While techniques exist for desensitizing features to common noise patterns produced by Speech-to-Text (STT)…
People commonly communicate in English, Arabic, and Bengali spoken languages through various mediums. However, deaf and hard-of-hearing individuals primarily use body language and sign language to express their needs and achieve…
Sign language is an essential resource enabling access to communication and proper socioemotional development for individuals suffering from disabling hearing loss. As this population is expected to reach 700 million by 2050, the importance…
Code-switching (CS) is a common phenomenon and recognizing CS speech is challenging. But CS speech data is scarce and there' s no common testbed in relevant research. This paper describes the design and main outcomes of the ASRU 2019…
"Transcription bottlenecks", created by a shortage of effective human transcribers are one of the main challenges to endangered language (EL) documentation. Automatic speech recognition (ASR) has been suggested as a tool to overcome such…
Automatic Speech Recognition (ASR) systems can be trained to achieve remarkable performance given large amounts of manually transcribed speech, but large labeled data sets can be difficult or expensive to acquire for all languages of…
In this paper, a novel approach is proposed for the recognition of Persian phonemes in the Persian Consonant-Vowel Combination (PCVC) speech dataset. Nowadays, deep neural networks play a crucial role in classification tasks. However, the…
Bangla is a language spoken by approximately 240 million native speakers and around 300 million people worldwide. Despite being the 5th largest spoken language in the world, Bangla is still a "low-resource" language, and existing pretrained…
Multilingual training is effective in improving low-resource ASR, which may partially be explained by phonetic representation sharing between languages. In end-to-end (E2E) ASR systems, graphemes are often used as basic modeling units,…
We introduce FLEURS, the Few-shot Learning Evaluation of Universal Representations of Speech benchmark. FLEURS is an n-way parallel speech dataset in 102 languages built on top of the machine translation FLoRes-101 benchmark, with…
Automatic Speech Recognition (ASR) is an active field of research due to its large number of applications and the proliferation of interfaces or computing devices that can support speech processing. However, the bulk of applications are…
Tibetan, one of the major low-resource languages in Asia, presents unique linguistic and sociocultural characteristics that pose both challenges and opportunities for AI research. Despite increasing interest in developing AI systems for…
This paper introduces FunASR, an open-source speech recognition toolkit designed to bridge the gap between academic research and industrial applications. FunASR offers models trained on large-scale industrial corpora and the ability to…
The current public datasets for speech recognition (ASR) tend not to focus specifically on the fairness aspect, such as performance across different demographic groups. This paper introduces a novel dataset, Fair-Speech, a publicly released…
We present an analysis of semi-supervised acoustic and language model training for English-isiZulu code-switched ASR using soap opera speech. Approximately 11 hours of untranscribed multilingual speech was transcribed automatically using…