3 papers
eess.AS2026
Latent Softmax for Data-Efficient Phoneme-Based Multilingual ASR Across Tonal and Non-Tonal Languages
Saierdaer Yusuyin, Nanling Jiang, Hao Huang +1
Phoneme-based multilingual automatic speech recognition (ASR) can share acoustic evidence across languages more directly than language-specific subword modeling. When tonal and non…
eess.AS2025
Pronunciation-Lexicon Free Training for Phoneme-based Crosslingual ASR via Joint Stochastic Approximation
Saierdaer Yusuyin, Te Ma, Hao Huang +1
Recently, pre-trained models with phonetic supervision have demonstrated their advantages for crosslingual speech recognition in data efficiency and information sharing across lang…
cs.SD2025
LLM-based phoneme-to-grapheme for phoneme-based speech recognition
Te Ma, Min Bi, Saierdaer Yusuyin +2
In automatic speech recognition (ASR), phoneme-based multilingual pre-training and crosslingual fine-tuning is attractive for its high data efficiency and competitive results compa…