Cantonese

The 'Cantonese' dataset/benchmark contains speech data used to evaluate cross-dialect speech recognition performance, particularly in the context of a unified framework that utilizes a Pinyin intermediate representation.

Papers using Cantonese (3)

Toward Unified Chinese Multi-Dialectal Speech Recognition via Pinyin Intermediate Representation2026A Novel Chinese Dialect TTS Frontend with Non-Autoregressive Neural Machine Translation2022 · 2 citesText Enhancement for Paragraph Processing in End-to-End Code-switching TTS2022