the speech enhancement techniques are often employed to improve the quality and intelligibility of the noisy speech signals. this paper discusses a novel technique for speech enhancement which is based on singular value decomposition. this implementation utilizes a genetic algorithm based optimization method for reducing the effects of environmental noises from the singular vectors as well as t...

This paper discusses design principles for spoken language applications. We focus on those aspects of interface design that are separate from basic speech recognition and that are concerned with the global process of performing a task using a speech interface. Six basic speech user interface design principles are discussed: 1. User plasticity. This property describes how much users can adapt to...

In the last few years, the focus in ASR research has shifted from the recognition of clean read speech (i.e. WSJ) to the more challenging task of transcribing found speech like broadcast news (Hub-4 task) and telephone conversations (Switchboard). Available training corpora tend to become larger and more erroneous than before, as transcribing found speech is more difficult. In this paper we pre...

The REVERB challenge provides a common framework for the evaluation of feature extraction techniques in the presence of both reverberation and additive background noise. State-of-the-art speech recognition systems perform well in controlled environments, but their performance degrades in realistic acoustical conditions, especially in real as well as simulated reverberant environments. In this c...

This paper gives an overview of the evaluation campaign results of the International Workshop on Spoken Language Translation (IWSLT) 20081. In this workshop, we focused on the translation of spontaneous speech recorded in a real situation and the feasability of pivot-language-based translation approaches. The translation directions were English into Chinese and vice versa for the Challenge Task...