VoxPopuli

VoxPopuli is a benchmark dataset used to evaluate the performance of Automatic Speech Recognition (ASR) models, specifically in the context of the Polish language.

Papers using VoxPopuli (14)

Joint Pre-training With Speech And Bilingual Text For Direct Speech To Speech Translation2022 · 11 citesDynamic Chunk Convolution For Unified Streaming And Non-streaming Conformer ASR2023 · 7 citesQuality of Automatic Speech Recognition -- Polish Language case study -- from Wav2Vec to Scribe ElevenLabs2026Speech Vecalign: an Embedding-based Method for Aligning Parallel Speech Documents2025CMU's IWSLT 2025 Simultaneous Speech Translation System2025On the use of Performer and Agent Attention for Spoken Language Identification2025Towards Personalization Of CTC Speech Recognition Models With Contextual Adapters And Adaptive Boosting2022Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models2022 · 5 citesSpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations2022 · 4 citesJoint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation2022 · 2 citesTowards Personalization of CTC Speech Recognition Models with Contextual Adapters and Adaptive Boosting2022Dynamic Chunk Convolution for Unified Streaming and Non-Streaming Conformer ASR2023DENOASR: Debiasing ASRs through Selective Denoising2024Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech2022