Az értekezés abból a feltételezésből indul ki, hogy beszéd prozódiai jelenségei, egy társas interakció zenei vetületeként, a verbális tartalom hiányában is informatívak lehetnek a társalgások makrostruktúráját és egyéb jellemzőit érintő vizsgálatokhoz. A hipotézisek ellenőrzésére percepciós kísérletekkel, illetve olyan, mesterséges intellingenciát alkalmazó klasszifikációs feladatokkal került sor, amelyekben a neurális hálózatokat egy saját fejlesztésű a beszéd intonációs eseményeit automatikusan lejegyző eljárás kimenetével tanítottuk be.The dissertation is based on the assumption that the prosodic phenomena of speech, as a musical aspect of a social interaction, may be informative for studies of the macrostructure and other characteristic...
In this paper, I present high-level speaker specific feature extraction considering intonation, ling...
In this paper, we propose a new approach for extracting and representing prosodic features directly ...
A crucial step in processing speech audio data for information extraction, topic detection, or brows...
This study is about an approach that formulates an explicit way from continuous acoustic parameters ...
The present communication concerns the use of prosodic parameters in automatic speech recognition (A...
We describe a “direct modeling ” approach to using prosody in various speech technology tasks. The a...
Correct pronunciation of spoken language requires the appropriate modulation of acoustic characteris...
Prozodija je važan aspekt govora jer poboljšava informativnost izgovorenog. Jedan segment prozodije ...
In this paper we show how prosody can be used in spo-ken dialog systems. First, we describe the phen...
In this article we propose two algorithms for discourse prosodic feature interpretation. The first a...
Prosodic research in recent years has been supported by a number of automatic analysis tools aimed a...
Bu makalede, bürünsel özniteliklerin gürültü içeren ortamlarda konuşmacı tanıma başarımına etkileri ...
La prosodia sirve para denominar a determinadas magnitudes físicas que pueden ser medidas en las señ...
In this paper we want to bridge the gap between pho-netic/phonological theory on the one hand and au...
International audienceThis paper presents an automatic approach for the detection of the prosodic st...
In this paper, I present high-level speaker specific feature extraction considering intonation, ling...
In this paper, we propose a new approach for extracting and representing prosodic features directly ...
A crucial step in processing speech audio data for information extraction, topic detection, or brows...
This study is about an approach that formulates an explicit way from continuous acoustic parameters ...
The present communication concerns the use of prosodic parameters in automatic speech recognition (A...
We describe a “direct modeling ” approach to using prosody in various speech technology tasks. The a...
Correct pronunciation of spoken language requires the appropriate modulation of acoustic characteris...
Prozodija je važan aspekt govora jer poboljšava informativnost izgovorenog. Jedan segment prozodije ...
In this paper we show how prosody can be used in spo-ken dialog systems. First, we describe the phen...
In this article we propose two algorithms for discourse prosodic feature interpretation. The first a...
Prosodic research in recent years has been supported by a number of automatic analysis tools aimed a...
Bu makalede, bürünsel özniteliklerin gürültü içeren ortamlarda konuşmacı tanıma başarımına etkileri ...
La prosodia sirve para denominar a determinadas magnitudes físicas que pueden ser medidas en las señ...
In this paper we want to bridge the gap between pho-netic/phonological theory on the one hand and au...
International audienceThis paper presents an automatic approach for the detection of the prosodic st...
In this paper, I present high-level speaker specific feature extraction considering intonation, ling...
In this paper, we propose a new approach for extracting and representing prosodic features directly ...
A crucial step in processing speech audio data for information extraction, topic detection, or brows...