Browse > Speech > Large Vocabulary Continuous Speech Recognition

Large Vocabulary Continuous Speech Recognition

10 papers with code · Speech

State-of-the-art leaderboards

No evaluation results yet. Help compare methods by submit evaluation metrics.

Greatest papers with code

First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs

12 Aug 2014baidu-research/warp-ctc

Recent work demonstrated the feasibility of discarding the HMM sequence modeling framework by directly predicting transcript text from audio. This approach to decoding enables first-pass speech recognition with a language model, completely unaided by the cumbersome infrastructure of HMM-based systems.

LANGUAGE MODELLING LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION SPEECH RECOGNITION

End-to-End Attention-based Large Vocabulary Speech Recognition

18 Aug 2015rizar/attention-lvcsr

Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs). Most of these systems contain separate components that deal with the acoustic modelling, language modelling and sequence decoding.

ACOUSTIC MODELLING LANGUAGE MODELLING LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION SPEECH RECOGNITION

Attention-based Audio-Visual Fusion for Robust Automatic Speech Recognition

5 Sep 2018georgesterpu/Sigmedia-AVSR

Automatic speech recognition can potentially benefit from the lip motion patterns, complementing acoustic speech to improve the overall recognition performance, particularly in noise. In this paper we propose an audio-visual fusion strategy that goes beyond simple feature concatenation and learns to automatically align the two modalities, leading to enhanced representations which increase the recognition accuracy in both clean and noisy conditions.

LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

Trace norm regularization and faster inference for embedded speech recognition RNNs

ICLR 2018 paddlepaddle/farm

We propose and evaluate new techniques for compressing and speeding up dense matrix multiplications as found in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR). For compression, we introduce and study a trace norm regularization technique for training low rank factored versions of matrix multiplications.

LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION SPEECH RECOGNITION

Deep-FSMN for Large Vocabulary Continuous Speech Recognition

4 Mar 2018yangxueruivs/DFSMN

In this paper, we present an improved feedforward sequential memory networks (FSMN) architecture, namely Deep-FSMN (DFSMN), by introducing skip connections between memory blocks in adjacent layers. In a 20000 hours Mandarin recognition task, the LFR trained DFSMN can achieve more than 20% relative improvement compared to the LFR trained BLSTM.

LANGUAGE MODELLING LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION SPEECH RECOGNITION

A Survey of Recent DNN Architectures on the TIMIT Phone Recognition Task

19 Jun 2018OrcusCZ/NNAcousticModeling

In this survey paper, we have evaluated several recent deep neural network (DNN) architectures on a TIMIT phone recognition task. Also, we prefer the phone recognition task because it is much more sensitive to an acoustic model quality than a large vocabulary continuous speech recognition (LVCSR) task.

LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION SPEECH RECOGNITION

Recurrent DNNs and its Ensembles on the TIMIT Phone Recognition Task

19 Jun 2018OrcusCZ/NNAcousticModeling

Also, we prefer the phone recognition task because it is much more sensitive to an acoustic model quality than a large vocabulary continuous speech recognition task. The dropout was used as the regularization technique in most cases, but combination with other regularization techniques together with model ensembles was omitted.

LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

A segmental framework for fully-unsupervised large-vocabulary speech recognition

22 Jun 2016kamperh/recipe_bucktsong_awe

Our system uses a Bayesian modelling framework with segmental word representations: each word segment is represented as a fixed-dimensional acoustic embedding obtained by mapping the sequence of feature frames to a single embedding vector. We also show that the discovered clusters can be made less speaker- and gender-specific by using an unsupervised autoencoder-like feature extractor to learn better frame-level features (prior to embedding).

LANGUAGE MODELLING LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION SPEECH RECOGNITION