14 citations · 41 across the 15 of their papers we have counts for
15 papers
HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR
Hainan Xu, Travis M. Bartley, Vladimir Bataev +1
We present Hybrid-Autoregressive INference TrANsducers (HAINAN), a novel architecture for speech recognition that extends the Token-and-Duration Transducer (TDT) model. Trained wit…
Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation
Nithin Rao Koluguri, Travis Bartley, Hainan Xu +4
This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on sh…
Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU
Daniel Galvez, Vladimir Bataev, Hainan Xu +1
The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle ~80% of…
Label-Looping: Highly Efficient Decoding for Transducers
Vladimir Bataev, Hainan Xu, Daniel Galvez +2
This paper introduces a highly efficient greedy decoding algorithm for Transducer-based speech recognition models. We redesign the standard nested-loop design for RNN-T decoding, s…
Transducers with Pronunciation-aware Embeddings for Automatic Speech Recognition
Hainan Xu, Zhehuai Chen, Fei Jia +1
This paper proposes Transducers with Pronunciation-aware Embeddings (PET). Unlike conventional Transducers where the decoder embeddings for different tokens are trained independent…
Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition
Dongji Gao, Hainan Xu, Desh Raj +3
Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform "non-verbatim" transcription, whic…
Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts
Dongji Gao, Matthew Wiesner, Hainan Xu +3
This paper presents a novel algorithm for building an automatic speech recognition (ASR) model with imperfect training data. Imperfectly transcribed speech is a prevalent issue in…
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
Hainan Xu, Fei Jia, Somshubra Majumdar +3
This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by jointly pred…
Multi-blank Transducers for Speech Recognition
Hainan Xu, Fei Jia, Somshubra Majumdar +2
This paper proposes a modification to RNN-Transducer (RNN-T) models for automatic speech recognition (ASR). In standard RNN-T, the emission of a blank symbol consumes exactly one i…
An Asynchronous WFST-Based Decoder For Automatic Speech Recognition
Hang Lv, Zhehuai Chen, Hainan Xu +3
We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech…
Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
Yiming Wang, Tongfei Chen, Hainan Xu +7
We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neu…
Saliency-driven Word Alignment Interpretation for Neural Machine Translation
Shuoyang Ding, Hainan Xu, Philipp Koehn
Despite their original goal to jointly learn to align and translate, Neural Machine Translation (NMT) models, especially Transformer, are often perceived as not learning interpreta…
Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling
Hainan Xu, Shuoyang Ding, Shinji Watanabe
Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence…
A GPU-based WFST Decoder with Exact Lattice Generation
Zhehuai Chen, Justin Luitjens, Hainan Xu +3
We describe initial work on an extension of the Kaldi toolkit that supports weighted finite-state transducer (WFST) decoding on Graphics Processing Units (GPUs). We implement token…
Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline
Szu-Jui Chen, Aswin Shanmugam Subramanian, Hainan Xu +1
This paper describes a new baseline system for automatic speech recognition (ASR) in the CHiME-4 challenge to promote the development of noisy ASR in speech processing communities…