Browse > Speech > End-To-End Speech Recognition

End-To-End Speech Recognition

21 papers with code · Speech

Leaderboards

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Latest papers with code

CAT: CRF-based ASR Toolkit

20 Nov 2019thu-spmi/cat

In this paper, we present a new open source toolkit for automatic speech recognition (ASR), named CAT (CRF-based ASR Toolkit).

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

62
20 Nov 2019

RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation

8 May 2019rwth-i6/returnn

To the best knowledge of the authors, the results obtained when training on the full LibriSpeech training set, are the best published currently, both for the hybrid DNN/HMM and the attention-based systems.

END-TO-END SPEECH RECOGNITION LANGUAGE MODELLING SPEECH RECOGNITION

224
08 May 2019

Very Deep Self-Attention Networks for End-to-End Speech Recognition

30 Apr 2019quanpn90/NMTGMinor

Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community.

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

40
30 Apr 2019

SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

18 Apr 2019mozilla/DeepSpeech

On LibriSpeech, we achieve 6. 8% WER on test-other without the use of a language model, and 5. 8% WER with shallow fusion with a language model.

#3 best model for Speech Recognition on LibriSpeech test-clean (using extra training data)

DATA AUGMENTATION END-TO-END SPEECH RECOGNITION LANGUAGE MODELLING SPEECH RECOGNITION

13,171
18 Apr 2019

Jasper: An End-to-End Convolutional Neural Acoustic Model

5 Apr 2019NVIDIA/OpenSeq2Seq

In this paper, we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data.

END-TO-END SPEECH RECOGNITION LANGUAGE MODELLING SPEECH RECOGNITION

1,158
05 Apr 2019

End-To-End Speech Recognition Using A High Rank LSTM-CTC Based Model

12 Mar 2019mobvoi/lstm_ctc

In this paper, we propose to use a high rank projection layer to replace the projection matrix.

DATA AUGMENTATION END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

29
12 Mar 2019

Self-Attention Networks for Connectionist Temporal Classification in Speech Recognition

22 Jan 2019aaaceo890/Attention

The success of self-attention in NLP has led to recent applications in end-to-end encoder-decoder architectures for speech recognition.

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

1
22 Jan 2019

Optimal Completion Distillation for Sequence Learning

ICLR 2019 SaeedNajafi/OCD-Learning

We present Optimal Completion Distillation (OCD), a training procedure for optimizing sequence to sequence models based on edit distance.

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

12
02 Oct 2018

End-to-end speech recognition using lattice-free MMI

Interspeech 2018 2018 kaldi-asr/kaldi

We present our work on end-to-end training of acoustic models using the lattice-free maximum mutual information (LF-MMI) objective function in the context of hidden Markov models.

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

8,308
06 Sep 2018

End-to-End Speech Recognition From the Raw Waveform

19 Jun 2018renyuanL/ry-Speech-commands

In this paper, we study end-to-end systems trained directly from the raw waveform, building on two alternatives for trainable replacements of mel-filterbanks that use a convolutional architecture.

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

2
19 Jun 2018