研究论文

• 《Zipformer: A faster and better encoder for automatic speech recognition》2026-07-03
  The Conformer has become the most popular encoder model for automatic speech recognition (ASR). It adds convolution modules to a transformer to learn both local and global dependencies. In this work we describe a faster…
• 测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美2026-07-10
  测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美测试机器到位十全十美
• 《Pruned RNN-T for fast, memory-efficient ASR training》2026-07-01
  The RNN-Transducer (RNN-T) framework for speech recognition has been growing in popularity, particularly for deployed real-time ASR systems, because it combines high accuracy with naturally streaming recognition. One of…
• 《Cr-ctc: Consistency regularization on ctc for improved speech recognition》2026-07-01
  Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it often falls short in recognition performa…