Results 171 to 180 of about 19,826 (210)
Some of the next articles are maybe not open access.
Active learning for automatic speech recognition
IIEEE International Conference on Acoustics Speech and Signal Processing, 2002State-of-the-art speech recognition systems are trained using transcribed utterances, preparation of which is labor intensive and time-consuming. In this paper, we describe a new method for reducing the transcription effort for training in automatic speech recognition (ASR). Active learning aims at reducing the number of training examples to be labeled
Riccardi, Giuseppe, D. Tur, A. Gorin
openaire +3 more sources
2020
There are basically two application modes for automatic speech recognition (ASR): using speech as spoken input or as knowledge source. Spoken input addresses applications like dictation systems and navigation (transactional) systems. Using speech as a knowledge source has applications like multimedia indexing systems. The chapter presents the stages of
openaire +4 more sources
There are basically two application modes for automatic speech recognition (ASR): using speech as spoken input or as knowledge source. Spoken input addresses applications like dictation systems and navigation (transactional) systems. Using speech as a knowledge source has applications like multimedia indexing systems. The chapter presents the stages of
openaire +4 more sources
Automatic Speech Recognition and Intrinsic Speech Variation
2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings, 2006This paper briefly reviews state of the art related to the topic of speech variability sources in automatic speech recognition systems. It focuses on some variations within the speech signal that make the ASR task difficult. The variations detailed in the paper are intrinsic to the speech and affect the different levels of the ASR processing chain. For
BENZEGUIBA M. +12 more
openaire +2 more sources
2015 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON), 2015
This Plenary presents automatic speech recognition (ASR) as a task of artificial intelligence. The basis, the methodology, spectral processing, distance measures for speech, segmentation speech, spectral and temporal variability, application of Markov Models, noise robustness, Language Models for ASR, are presented.
Dong Yu, Li Deng
openaire +2 more sources
This Plenary presents automatic speech recognition (ASR) as a task of artificial intelligence. The basis, the methodology, spectral processing, distance measures for speech, segmentation speech, spectral and temporal variability, application of Markov Models, noise robustness, Language Models for ASR, are presented.
Dong Yu, Li Deng
openaire +2 more sources
1997
Sound waves in general and speech in particular consist of disturbances traveling through the air. These disturbances are described by the air displacement, air density, and air pressure. All of these quantities are time and space dependent. Sound waves have the following properties which may be either confirmed experimentally or derived from physical ...
openaire +5 more sources
Sound waves in general and speech in particular consist of disturbances traveling through the air. These disturbances are described by the air displacement, air density, and air pressure. All of these quantities are time and space dependent. Sound waves have the following properties which may be either confirmed experimentally or derived from physical ...
openaire +5 more sources
2009
Automatic speech recognition (ASR) is a critical component for CHIL services. For example, it provides the input to higher-level technologies, such as summarization and question answering, as discussed in Chapter 8. In the spirit of ubiquitous computing, the goal of ASR in CHIL is to achieve a high performance using far-field sensors (networks of ...
Gerasimos Potamianos +10 more
openaire +2 more sources
Automatic speech recognition (ASR) is a critical component for CHIL services. For example, it provides the input to higher-level technologies, such as summarization and question answering, as discussed in Chapter 8. In the spirit of ubiquitous computing, the goal of ASR in CHIL is to achieve a high performance using far-field sensors (networks of ...
Gerasimos Potamianos +10 more
openaire +2 more sources
2021
This chapter is entirely dedicated to automatic speech recognition (ASR) which is one of the most complex fields of machine learning. Topics from signal processing and the properties of the acoustic signal to acoustic and language modeling, pronunciation modeling and performance analysis will all be explained in an easily comprehensible manner.
openaire +1 more source
This chapter is entirely dedicated to automatic speech recognition (ASR) which is one of the most complex fields of machine learning. Topics from signal processing and the properties of the acoustic signal to acoustic and language modeling, pronunciation modeling and performance analysis will all be explained in an easily comprehensible manner.
openaire +1 more source
The Journal of the Acoustical Society of America, 2007
A system for responding to spoken commands enables a computer system to avoid some synchronization problems. In certain embodiments, object oriented programming may be utilized to create an object which seamlessly coordinates between an application program and a speech engine.
openaire +1 more source
A system for responding to spoken commands enables a computer system to avoid some synchronization problems. In certain embodiments, object oriented programming may be utilized to create an object which seamlessly coordinates between an application program and a speech engine.
openaire +1 more source
2019
Automatic speech recognition (ASR) has grown tremendously in recent years, with deep learning playing a key role. Simply put, ASR is the task of converting spoken language into computer readable text (Fig. 8.1). It has quickly become ubiquitous today as a useful way to interact with technology, significantly bridging in the gap in human–computer ...
Uday Kamath, John Liu, James Whitaker
openaire +1 more source
Automatic speech recognition (ASR) has grown tremendously in recent years, with deep learning playing a key role. Simply put, ASR is the task of converting spoken language into computer readable text (Fig. 8.1). It has quickly become ubiquitous today as a useful way to interact with technology, significantly bridging in the gap in human–computer ...
Uday Kamath, John Liu, James Whitaker
openaire +1 more source
2014
In this chapter we describe techniques to build a high performance speech recognizer for Arabic and related languages. The key insights are derived from our experience in the DARPA GALE program, a 5-year program devoted to enhancing the state-of-the-art in Arabic speech recognition and translation.
Hagen Soltau +6 more
openaire +1 more source
In this chapter we describe techniques to build a high performance speech recognizer for Arabic and related languages. The key insights are derived from our experience in the DARPA GALE program, a 5-year program devoted to enhancing the state-of-the-art in Arabic speech recognition and translation.
Hagen Soltau +6 more
openaire +1 more source