Search Results for author:
Found 21 papers, 7 papers with code
Three-in-One: Fast and Accurate Transducer for Hybrid-Autoregressive ASR
We present \textbf{H}ybrid-\textbf{A}utoregressive \textbf{IN}ference Tr\textbf{AN}sducers (HAINAN), a novel architecture for speech recognition that extends the Token-and-Duration Transducer (TDT) model.
Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation
Additionally, training on longer audio segments increases the overall model accuracy across speech recognition and translation benchmarks.
Romanization Encoding For Multilingual ASR
Ablation studies on Mandarin-Korean and Mandarin-Japanese highlight our method's strong capability to address the complexities of other script-heavy languages, paving the way for more versatile and effective multilingual ASR systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Label-Looping: Highly Efficient Decoding for Transducers
This paper introduces a highly efficient greedy decoding algorithm for Transducer-based speech recognition models.
Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU
The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on decoding.
Transducers with Pronunciation-aware Embeddings for Automatic Speech Recognition
This paper proposes Transducers with Pronunciation-aware Embeddings (PET).
TDT-KWS: Fast And Accurate Keyword Spotting Using Token-and-duration Transducer
Designing an efficient keyword spotting (KWS) system that delivers exceptional performance on resource-constrained edge devices has long been a subject of significant attention.
Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition
Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts
Imperfectly transcribed speech is a prevalent issue in human-annotated speech corpora, which degrades the performance of ASR models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
TDT models for Speech Recognition achieve better accuracy and up to 2. 82X faster inference than conventional Transducers.
Intent Classification
Intent Classification and Slot Filling
+3
Multi-blank Transducers for Speech Recognition
This paper proposes a modification to RNN-Transducer (RNN-T) models for automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
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 neural machine translation toolkit fairseq.
Ranked #1 on
Speech Recognition
on Hub5'00 CallHome
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
Saliency-driven Word Alignment Interpretation for Neural Machine Translation
Despite their original goal to jointly learn to align and translate, Neural Machine Translation (NMT) models, especially Transformer, are often perceived as not learning interpretable word alignments.
Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling
Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words.
The JHU Parallel Corpus Filtering Systems for WMT 2018
This work describes our submission to the WMT18 Parallel Corpus Filtering shared task.
Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks
Time Delay Neural Networks (TDNNs), also known as onedimensional Convolutional Neural Networks (1-d CNNs), are an efficient and well-performing neural network architecture for speech recognition.
Neural Network Language Modeling with Letter-based Features and Importance Sampling
In this paper we describe an extension of the Kaldi software toolkit to support neural-based language modeling, intended for use in automatic speech recognition (ASR) and related tasks.
Ranked #42 on
Speech Recognition
on LibriSpeech test-other
(using extra training data)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
A GPU-based WFST Decoder with Exact Lattice Generation
We describe initial work on an extension of the Kaldi toolkit that supports weighted finite-state transducer (WFST) decoding on Graphics Processing Units (GPUs).
Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline
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 by providing 1) state-of-the-art system with a simplified single system comparable to the complicated top systems in the challenge, 2) publicly available and reproducible recipe through the main repository in the Kaldi speech recognition toolkit.
Ranked #2 on
Noisy Speech Recognition
on CHiME real
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Zipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora
We introduce Zipporah, a fast and scalable data cleaning system.
