1
Image of Reverse engineering: infant language acquisition
Reverse engineering: infant language acquisition
Reverse engineering: infant language acquisition by Emmanuel Dupoux. [Read More]
1
Image of Recent progress in unsupervised speech processing
Recent progress in unsupervised speech processing
The development of an automatic speech recognizer is typically a highly supervised process involving the specification of phonetic inventories, lexicons, acoustic and language models, along with annot... [Read More]
1
Image of Outing unfortunate characteristics of HHMS
Outing unfortunate characteristics of HHMS
Hidden Markov models (HMMs) have been applied to the problem of automatic speech recognition for more than 40 years and today HMMs are used in nearly all commercial and research speech recognition sys... [Read More]
1
Image of Multilayer perceptrons for speech recognition
Multilayer perceptrons for speech recognition
This presentation will describe the long journey from early speech classification experiments with MLPs in the 1960s to the present day implementations. [Read More]
1
Image of Context-dependent deep neural networks for large vocabulary speech recognition
Context-dependent deep neural networks for large vocabulary speech recognition
This is arguably the largest gain obtained through a single technology in ASR. This talk will describe how this discovery has been further developed towards use in practical systems. [Read More]
1
Image of Closing discussion ASRU 2013
Closing discussion ASRU 2013
Closing discussion ASRU 2013 What´s wrong with ASR and what can we do about it. [Read More]
1
Image of Calibration of binary and multiclass probabilistic classifiers
Calibration of binary and multiclass probabilistic classifiers
Automatic pattern classifiers that output soft, probabilistic classifications can be more widely and more profitably applied, provided the probabilistic output is well-calibrated. [Read More]
1
Image of Building speech recognition systems with low resources
Building speech recognition systems with low resources
Large-scale data resources are currently available for a minority of languages and the costs for data collections are prohibitive to all but the most widely spoken and economically viable languages. [Read More]
1
Image of ASRU 2013 closing
ASRU 2013 closing
ASRU 2013 closing and Best poster prize. The ASRU workshop meets every two years and has a tradition of bringing together researchers from academia and industry in an intimate and collegial setting to... [Read More]
1
Image of Augmenting conversations with search engine
Augmenting conversations with search engine
This presentation will show how speech recognition, natural language processing, and information retrieval techniques are being combined to drive an innovative anticipatory search engine. [Read More]
1
Image of ASRU 2013 opening
ASRU 2013 opening
ASRU 2013 opening, announcing best paper and best student paper prizes. [Read More]
1
Image of The neural mechanisms of speech production
The neural mechanisms of speech production
Speech production is a highly complex sensorimotor task involving tightly coordinated processing in the frontal, temporal, and parietal lobes of the cerebral cortex. [Read More]
1
Image of Spoken content retrieval
Spoken content retrieval
Multimedia content over the Internet is very attractive, while the spoken part of such content very often tells the core information. It is therefore possible to index, retrieve or browse multimedia c... [Read More]
1
Image of Speech synthesis as a statistical machine learning problem
Speech synthesis as a statistical machine learning problem
Speech synthesis is often regarded as a messy problem. This talk will discuss how we can formulate the problem of speech synthesis in a statistical machine learning framework. [Read More]
1
Image of Robust speech recognition
Robust speech recognition
The robustness of speech recognition systems to acoustic variability is a key factor to their success or failure. [Read More]
1
Image of More words and bigger pictures
More words and bigger pictures
Object recognition is a little like translation: a picture (text in a source language) goes in, and a description (text in a target language) comes out. I will use this analogy, which has proven ferti... [Read More]
1
Image of Efficient algorithms for learning sparse models
Efficient algorithms for learning sparse models
We will review the design, analysis and implementation of several sparsity promoting learning algorithms. [Read More]
1
Image of Behavioral signal processing
Behavioral signal processing
The expression and experience of human behavior are complex and multimodal, and are characterized by individual and contextual heterogeneity and variability. Speech and spoken language communication c... [Read More]
1
Image of Automatic translation of talks
Automatic translation of talks
This task presents several interesting research issues for speech recognition and speech translation technology, such as open domain ASR and MT, clean transcription of spontaneous speech, talk style a... [Read More]
1
Image of Petr Ludwig
Petr Ludwig
Petr Ludwig se zabývá bouráním polopravd a mýtů v oblasti osobního rozvoje. Za tímto účelem založil vzdělávací institut GrowJOB. [Read More]