Browse > Speech > End-To-End Speech Recognition

End-To-End Speech Recognition

21 papers with code ยท Speech

Leaderboards

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Latest papers without code

Imputer: Sequence Modelling via Imputation and Dynamic Programming

20 Feb 2020

This paper presents the Imputer, a neural sequence model that generates output sequences iteratively via imputations.

END-TO-END SPEECH RECOGNITION IMPUTATION SPEECH RECOGNITION

Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language

16 Feb 2020

Ainu is an unwritten language that has been spoken by Ainu people who are one of the ethnic groups in Japan.

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

Small energy masking for improved neural network training for end-to-end speech recognition

15 Feb 2020

More specifically, a time-frequency bin is masked if the filterbank energy in this bin is less than a certain energy threshold.

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR

14 Feb 2020

We propose an unsupervised speaker adaptation method inspired by the neural Turing machine for end-to-end (E2E) automatic speech recognition (ASR).

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss

7 Feb 2020

We present results on the LibriSpeech dataset showing that limiting the left context for self-attention in the Transformer layers makes decoding computationally tractable for streaming, with only a slight degradation in accuracy.

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

Scaling Up Online Speech Recognition Using ConvNets

27 Jan 2020

We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC).

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

Semi-supervised ASR by End-to-end Self-training

24 Jan 2020

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue.

DATA AUGMENTATION END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

Data Techniques For Online End-to-end Speech Recognition

24 Jan 2020

Practitioners often need to build ASR systems for new use cases in a short amount of time, given limited in-domain data.

DATA AUGMENTATION DOMAIN ADAPTATION END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

Transformer-based Online CTC/attention End-to-End Speech Recognition Architecture

15 Jan 2020

To support the online recognition, we integrate the state reuse chunk-SAE and the MTA based SAD into online CTC/attention architecture.

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

Streaming automatic speech recognition with the transformer model

8 Jan 2020

Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR).

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION