Browse > Speech > Speech Recognition

Speech Recognition

211 papers with code · Speech

Speech recognition is the task of recognising speech within audio and converting it into text.

( Image credit: SpecAugment )

Leaderboards

Latest papers with code

Harnessing Evolution of Multi-Turn Conversations for Effective Answer Retrieval

22 Dec 2019aliannejadi/castur

With the improvements in speech recognition and voice generation technologies over the last years, a lot of companies have sought to develop conversation understanding systems that run on mobile phones or smart home devices through natural language interfaces.

SPEECH RECOGNITION

3
22 Dec 2019

Libri-Light: A Benchmark for ASR with Limited or No Supervision

17 Dec 2019facebookresearch/libri-light

Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-supervised setting (PER, CER) and (3) the distant supervision setting (WER).

ACTION DETECTION SPEECH RECOGNITION

57
17 Dec 2019

A Resource for Computational Experiments on Mapudungun

4 Dec 2019pywirrarika/naki

We present a resource for computational experiments on Mapudungun, a polysynthetic indigenous language spoken in Chile with upwards of 200 thousand speakers.

MACHINE TRANSLATION SPEECH RECOGNITION SPEECH SYNTHESIS

34
04 Dec 2019

Untangling in Invariant Speech Recognition

NeurIPS 2019 schung039/neural_manifolds_replicaMFT

Higher level concepts such as parts-of-speech and context dependence also emerge in the later layers of the network.

SPEECH RECOGNITION

4
01 Dec 2019

Kurdish (Sorani) Speech to Text: Presenting an Experimental Dataset

29 Nov 2019KurdishBLARK/BD-4SK-ASR

We present an experimental dataset, Basic Dataset for Sorani Kurdish Automatic Speech Recognition (BD-4SK-ASR), which we used in the first attempt in developing an automatic speech recognition for Sorani Kurdish.

SPEECH RECOGNITION

1
29 Nov 2019

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

56
20 Nov 2019

Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks

25 Oct 2019alecokas/BiLatticeRNN-Confidence

Experimental results using the IARPA OpenKWS 2016 evaluation system show that the use of additional information yields significant gains in confidence estimation accuracy.

SPEECH RECOGNITION

4
25 Oct 2019

ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit

24 Oct 2019espnet/espnet

Furthermore, the unified design enables the integration of ASR functions with TTS, e. g., ASR-based objective evaluation and semi-supervised learning with both ASR and TTS models.

SPEECH RECOGNITION

1,814
24 Oct 2019

Generative Pre-Training for Speech with Autoregressive Predictive Coding

23 Oct 2019iamyuanchung/Autoregressive-Predictive-Coding

Learning meaningful and general representations from unannotated speech that are applicable to a wide range of tasks remains challenging.

REPRESENTATION LEARNING SPEAKER IDENTIFICATION SPEECH RECOGNITION TRANSFER LEARNING

64
23 Oct 2019

FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing

29 Sep 2019yluo42/TAC

Beamforming has been extensively investigated for multi-channel audio processing tasks.

SPEECH ENHANCEMENT SPEECH RECOGNITION

14
29 Sep 2019