An annotation system for melodic aspects of German spontaneous speech
نویسندگان
چکیده
This article presents a phonetically de ned annotation system for German speech melody, whose descriptive units cover the perceptive relevant pitch movements. The units for the melodic annotation are based on the model for read German utterances [1]. The implementation of our descriptive melodic units as part of a recently developed labelling and testing environment for melodic aspects of speech allows a comfortable and intersubjective application of the melodic units for the annotation of speech. An experimental evaluation by a rating-experiment secures that the melodic units describe spontaneous speech as adequately as read speech
منابع مشابه
A comparative study of HMM-based approaches for the automatic recognition of perceptually relevant aspects of spontaneous German speech melody
Three approaches to the speaker independent automatic recognition of melodic aspects of spontaneous German are presented. All systems are based on Hidden Markov Models. Their input is restricted to the speech signal from which a feature extraction component derives eleven prosodic features. No additional information { as commonly used for prosody recognition { like word chains, word hypotheses,...
متن کاملA Comparative Study of Hmm - Basedapproaches for the Automaticrecognition of Perceptually Relevantaspects
Three approaches to the speaker independent automatic recognition of melodic aspects of spontaneous German are presented. All systems are based on Hidden Markov Models. Their input is restricted to the speech signal from which a feature extraction component derives eleven prosodic features. No additional information { as commonly used for prosody recognition { like word chains, word hypotheses,...
متن کاملAn environment for the labelling and testing of melodic aspects of speech
In this paper, we present an environment for labelling and testing of melodic aspects of spoken language. The environment has three modes of application: First, the environment provides labelling facilities for a model-based melodic description for German. Second, it supports a language independent pre-theoretical description of speech melody allowing the development of new melodic categories. ...
متن کاملFOLK-Gold ― A Gold Standard for Part-of-Speech-Tagging of Spoken German
In this paper, we present a GOLD standard of part-of-speech tagged transcripts of spoken German. The GOLD standard data consists of four annotation layers – transcription (modified orthography), normalization (standard orthography), lemmatization and POS tags – all of which have undergone careful manual quality control. It comes with guidelines for the manual POS annotation of transcripts of Ge...
متن کاملSLAM: Automatic Stylization and Labelling of Speech Melody
This paper presents SLAM : a simple method for the automatic Stylization and LAbelling of speech Melody. This main contributions over existing methods are : the alphabet of melodic contours is fully data-driven, an explicit time-frequency representation is used to derive complex melodic contours, and melodic contours can be determined over arbitrary prosodic/syntactic units. Additionally, the s...
متن کامل