SGPISpeech

SGPISpeech is a dataset used to evaluate continual learning strategies for end-to-end automatic speech recognition by fine-tuning models on specific speech data.

Papers using SGPISpeech (6)

SPGISpeech 2.0: Transcribed multi-speaker financial audio for speaker-tagged transcription2025 · 3 citesRetrieval Augmented Generation based context discovery for ASR2025 · 1 citesPrompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition2023 · 2 citesContinual Learning for End-to-End ASR by Averaging Domain Experts2023Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer2023Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation2024