Xiaohui Zhang

Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces

2020 · arXiv (Cornell University)

In this work, we first show that on the widely used LibriSpeech benchmark, our transformer-based context-dependent connectionist temporal classification (CTC) system produces state-of-the-art results. We then show that using wordpieces as modeling units combined with …

Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings

2021 · arXiv (Cornell University)

Speech recognition models often obtain degraded performance when tested on speech with unseen accents. Domain-adversarial training (DAT) and multi-task learning (MTL) are two common approaches for building accent-robust ASR models. ASR models using accent embeddings …

TST: Time-Sparse Transducer for Automatic Speech Recognition

2023 · arXiv (Cornell University)

End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence. To solve this problem, …

A Trusted Privacy-Preserving Model for Cross-Chain Transactions Based on zk_SNARKs

2023

Currently, the privacy protection technology of blockchain is not mature enough, such as user data leakage and lack of anonymity exist, and these problems are especially serious when conducting cross-chain transactions. In this paper, we …

From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition

2019 · 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

There is an implicit assumption that traditional hybrid approaches for automatic speech recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to get competitive performance, especially on English which has poor …