Acoustic Models for Posterior Features in Speech Recognition
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.
Audio segmentation, in general, is the task of segmenting a continuous audio stream in terms of acoustically homogenous regions, where the rule of homogeneity depends on the task. This thesis aims at developing and investigating efficient, robust and unsup ...
The paper proposes and discusses a machine approach for identification of unexpected (zero or low probability) words. The approach is based on use of two parallel recognition channels, one channel employing sensory information from the speech signal togeth ...
In this paper, we present initial investigations towards boosting posterior probability based speech recognition systems by estimating more informative posteriors taking into account acoustic context (e.g., the whole utterance), as well as possible prior i ...
The recognition of events in multimedia data is a challenging area of research. The growth in the amount of multimedia data being produced and stored increases the need for systems capable of automatically analysing this data. This analysis can aid in effi ...
Local state or phone posterior probabilities are often investigated as local scores (e.g., hybrid HMM/ANN systems) or as transformed acoustic features (e.g., ``Tandem'') to improve speech recogni tion systems. In this paper, we present initial results towa ...
In this paper, we show that the hinge loss can be interpreted as the neg-log-likelihood of a semi-parametric model of posterior probabilities. From this point of view, SVMs represent the parametric component of a semi-parametric model fitted by a maximum a ...
In a previous paper on speech recognition, we showed that templates can better capture the dynamics of speech signal compared to parametric models such as hidden Markov models. The key point in template matching approaches is finding the most similar templ ...
In this paper, we show that the hinge loss can be interpreted as the neg-log-likelihood of a semi-parametric model of posterior probabilities. From this point of view, SVMs represent the parametric component of a semi-parametric model fitted by a maximum a ...
Local state or phone posterior probabilities are often investigated as local scores (e.g., hybrid HMM/ANN systems) or as transformed acoustic features (e.g., ``Tandem'') to improve speech recogni tion systems. In this paper, we present initial results towa ...
Given the availability of large speech corpora, as well as the increasing of memory and computational resources, the use of template matching approaches for automatic speech recognition (ASR) have recently attracted new attention. In such template-based ap ...
