Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition
Publications associées (42)
Graph Chatbot
Chattez avec Graph Search
Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.
AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.
We investigate the effects of different silence modelling strategies in Weighted Finite-State Transducers for Automatic Speech Recognition. We show that the choice of silence models, and the way they are included in the transducer, can have a significant e ...
The work described in this thesis takes place in the context of capturing real-life audio for the analysis of spontaneous social interactions. Towards this goal, we wish to capture conversational and ambient sounds using portable audio recorders. Analysis ...
The work described in this thesis takes place in the context of capturing real-life audio for the analysis of spontaneous social interactions. Towards this goal, we wish to capture conversational and ambient sounds using portable audio recorders. Analysis ...
This paper investigates robust privacy-sensitive audio features for speaker diarization in multiparty conversations: ie., a set of audio features having low linguistic information for speaker diarization in a single and multiple distant microphone scenario ...
Recurrent neural network language models (RNNLMs) have recently shown to outperform the venerable n-gram language models (LMs). However, in automatic speech recognition (ASR), RNNLMs were not yet used to directly decode a speech signal. Instead, RNNLMs are ...
Juicer is a decoder for HMM-based large vocabulary speech recognition that uses a weighted finite state transducer (WFST) representation of the search space. The package consists of a number of command line utilities: the Juicer decoder itself, along with ...
We propose a generalized dynamic composition algorithm of weighted finite state transducers (WFST), which avoids the creation of non-coaccessible paths, performs weight look-ahead and does not impose any constraints to the topology of the WFSTs. Experiment ...
This paper investigates employment of Subspace Gaussian Mixture Models (SGMMs) for acoustic model adaptation towards different accents for English speech recognition. The SGMMs comprise globally-shared and state-specific parameters which can efficiently be ...
We describe the design of Kaldi, a free, open-source toolkit for speech recognition research. Kaldi provides a speech recognition system based on finite-state transducers (using the freely available OpenFst), together with detailed documentation and script ...
We investigate the effects of different silence modelling strategies in Weighted Finite-State Transducers for Automatic Speech Recognition. We show that the choice of silence models, and the way they are included in the transducer, can have a significant e ...