SEAME

The SEAME dataset contains labeled conversational Chinese-English code-switching speech and is used to evaluate automatic speech recognition (ASR) performance in multilingual contexts.

Papers using SEAME (10)

Adapting Whisper for Parameter-efficient Code-Switching Speech Recognition via Soft Prompt Tuning2025 · 2 citesImproving Code-Switching Speech Recognition with TTS Data Augmentation2026CAMEL: Cross-Attention Enhanced Mixture-of-Experts and Language Bias for Code-Switching Speech Recognition2024Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding2024Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition2022 · 5 citesLanguage-specific Acoustic Boundary Learning for Mandarin-English Code-switching Speech Recognition2023 · 2 citesReducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization2022 · 1 citesAdapting OpenAI's Whisper for Speech Recognition on Code-Switch Mandarin-English SEAME and ASRU2019 Datasets2023 · 1 citesRomanization Encoding For Multilingual ASR2024 · 1 citesEnhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection2024