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 report, we provide a theoretical discussion on temporal data cluster analysis: does the data come from one source or two sources; is it better to cluster the data into two clusters or leave it as one cluster. Here we analyse only the simplest case: ...
Latent variable decomposition permits factorisation of posterior probability based, or likelihood based, speech unit discriminant functions into a composition of simpler functions which can be analysed separately and evaluated more accurately in the presen ...
Automatic speech/music discrimination has been receiving importance recently, for example when large multimedia documents have to be processed by an ASR system, or for indexing and retrieval of such documents. This work presents using outputs of a speech r ...
In this paper we develop different mathematical models in the framework of the multi-stream paradigm for noise robust ASR, and discuss their close relationship with human speech perception. Largely inspired by Fletcher's "product-of-errors" rule in psychoa ...
An MLP classifier outputs a posterior probability for each class. With noisy data, classification becomes less certain, and the entropy of the posteriors distribution tends to increase providing a measure of classification confidence. However, at high nois ...
In this paper, we present and investigate a new method for subband-based Automatic Speech Recognition (ASR) which approximates the ideal full combination' approach which is itself often not practical to realize. The full combination' approach consists of ...
The conventional treatment for the cure of esophageal cancer is surgical resection. Esophageal cancer, when detected at an early stage, has a very good probability of being eradicated by less aggressive procedures, and photodynamic therapy has proven to be ...
An MLP classifier outputs a posterior probability for each class. With noisy data classification becomes less certain and the entropy of the posteriors distribution tends to increase, therefore providing a measure of classification confidence. However, at ...
In this paper we develop different mathematical models in the framework of the multi-stream paradigm for noise robust ASR, and discuss their close relationship with human speech perception. Largely inspired by Fletcher's "product-of-errors" rule in psychoa ...
This paper investigates an approach that maximizes the joint posterior probabil ity of the pronounced word and the speaker identity given the observed data. This probability can be expressed as a product of the posterior probability of the pronounced word ...
