Long short-term memory (LSTM; Hochreiter & Schmidhuber, 1997) can solve numerous
tasks not solvable by previous learning algorithms for recurrent neural networks (RNNs). We …

Recurrent networks (crossreference Chapter 12) can, in principle, use their feedback
connections to store representations of recent input events in the form of activations. The …

The temporal distance between events conveys information essential for numerous
sequential tasks such as motor control and rhythm detection. While Hidden Markov Models …

Sign language recognition is one of the fundamental ways to assist deaf people to
communicate with others. An accurate vision-based sign language recognition system using …

Tanja Schultz and Katrin Kirchhoff have compiled a comprehensive overview of speech
processing from a multilingual perspective. By taking this all-inclusive approach to speech …

In recent years, deep neural networks (DNNs) have achieved a remarkable progression in
solving many complex problems. DNNs are suitable for dealing with the problems related to …

The low frequency (LF) spectral analysis or 'rhythm spectrum'approach to the quantitative
analysis and comparison of speech rhythms is extended beyond syllable or word rhythms to …

This paper deals with an approach to automatic language identification based on rhythmic
modelling. Beside phonetics and phonotactics, rhythm is actually one of the most promising …

An approach to automatic language identification (LID) using pitch contour information is
proposed. A segment of pitch contour is approximated by a set of Legendre polynomials so …

Prosody is usually defined in terms of the three distinct but interacting domains of pitch,
intensity and duration patterning, or, more generally, as phonological and phonetic …