The Juicer LVCSR Decoder - User Manual for Juicer version 0.5.0
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
In this thesis, we investigate a hierarchical approach for estimating the phonetic class-conditional probabilities using a multilayer perceptron (MLP) neural network. The architecture consists of two MLP classifiers in cascade. The first MLP is trained in ...
Phoneme-based multilingual connectionist temporal classification (CTC) model is easily extensible to a new language by concatenating parameters of the new phonemes to the output layer. In the present paper, we improve cross-lingual adaptation in the contex ...
We propose a stochastic phoneme space transformation technique that allows the conversion of conditional source phoneme posterior probabilities (conditioned on the acoustics) into target phoneme posterior probabilities. The source and target phonemes can b ...
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 automata (using the freely available OpenFst), together with detailed documentation and a compreh ...
We propose a stochastic phoneme space transformation technique that allows the conversion of conditional source phoneme posterior probabilities (conditioned on the acoustics) into target phoneme posterior probabilities. The source and target phonemes can b ...
In this paper we propose a new technique for robust keyword spotting that uses bidirectional Long Short-Term Memory (BLSTM) recurrent neural nets to incorporate contextual information in speech decoding. Our approach overcomes the drawbacks of generative H ...
In Deep Neural Network (DNN) i-vector based speaker recognition systems, acoustic models trained for Automatic Speech Recognition are employed to estimate sufficient statistics for i-vector modeling. The DNN based acoustic model is typically trained on a w ...
Standard automatic speech recognition (ASR) systems follow a divide and conquer approach to convert speech into text. Alternately, the end goal is achieved by a combination of sub-tasks, namely, feature extraction, acoustic modeling and sequence decoding, ...
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 ...
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 ...
