Related papers: WorldSpeech: A Multilingual Speech Corpus from Aro…

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…

Building a high quality automatic speech recognition (ASR) system with limited training data has been a challenging task particularly for a narrow target population. Open-sourced ASR systems, trained on sufficient data from adults, are…

We present the Open ASR Leaderboard, a reproducible benchmarking platform with community contributions from academia and industry. It compares 86 open-source and proprietary systems across 12 datasets, with English short- and long-form and…

Speech technology remains out of reach for most of the over 2300 languages in Africa. We present the first systematic assessment of large-scale synthetic voice corpora for African ASR. We apply a three-step process: LLM-driven text…

Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues…

We introduce RO-N3WS, a benchmark Romanian speech dataset designed to improve generalization in automatic speech recognition (ASR), particularly in low-resource and out-of-distribution (OOD) conditions. RO-N3WS comprises over 126 hours of…

The existing audio datasets are predominantly tailored towards single languages, overlooking the complex linguistic behaviors of multilingual communities that engage in code-switching. This practice, where individuals frequently mix two or…

Nearly half of the world's languages are endangered. Speech technologies such as Automatic Speech Recognition (ASR) are central to revival efforts, yet most languages remain unsupported because standard pipelines expect utterance-level…

We introduce ParCzech4Speech 1.0, a processed version of the ParCzech 4.0 corpus, targeted at speech modeling tasks with the largest variant containing 2,695 hours. We combined the sound recordings of the Czech parliamentary speeches with…

Common measures of accuracy used to assess the performance of automatic speech recognition (ASR) systems, as well as human transcribers, conflate multiple sources of error. Stylistic differences, such as verbatim vs non-verbatim, can play a…

This paper introduces a new multi-speaker English dataset for training text-to-speech models. The dataset is based on LibriVox audiobooks and Project Gutenberg texts, both in the public domain. The new dataset contains about 292 hours of…

Police departments around the world use two-way radio for coordination. These broadcast police communications (BPC) are a unique source of information about everyday police activity and emergency response. Yet BPC are not transcribed, and…

Thanks to the rise of self-supervised learning, automatic speech recognition (ASR) systems now achieve near-human performance on a wide variety of datasets. However, they still lack generalization capability and are not robust to domain…

Spoken language understanding (SLU) is indispensable for half of all living languages that lack a formal writing system. Unlike for high-resource languages, for these languages, we cannot offload semantic understanding of speech to the…

Automatic speech recognition (ASR) systems have achieved near-human accuracy on curated benchmarks, yet still fail in real-world voice agents under conditions that current evaluations do not systematically cover. Without diagnostic tools…

In this report, we introduce Qwen3-ASR family, which includes two powerful all-in-one speech recognition models and a novel non-autoregressive speech forced alignment model. Qwen3-ASR-1.7B and Qwen3-ASR-0.6B are ASR models that support…

This study investigates the impact of integrating a dataset of disordered speech recordings ($\sim$1,000 hours) into the fine-tuning of a near state-of-the-art ASR baseline system. Contrary to what one might expect, despite the data being…

Speech datasets available in the public domain are often underutilized because of challenges in discoverability and interoperability. A comprehensive framework has been designed to survey, catalog, and curate available speech datasets,…

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

Paralinguistic sounds, like laughter and sighs, are crucial for synthesizing more realistic and engaging speech. However, existing methods typically depend on proprietary datasets, while publicly available resources often suffer from…