On the automatic toBI accent type identification from data
نویسندگان
چکیده
This contribution faces the ToBI accent recognition problem with the goal of multiclass identification vs. the more conservative Accent vs. No Accent approach. A neural network and a decision tree are used for automatic recognition of the ToBI accents in the Boston Radio Corpus. Multiclass classification results show the difficulty of the problem and the impact of imbalanced classes. A study of the confusion/similarity between accent types, based on in-pair recognition rates, shows its impact on the overall performance. More expressive F0 contours parametrization techniques have been used to improve recognition rates.
منابع مشابه
Analysis of Inconsistencies in Cross-Lingual Automatic ToBI Tonal Accent Labeling
This paper presents an experimental study on how corpus-based automatic prosodic information labeling can be transferred from a source language to a different target language. Tone accent identification models trained for Spanish, using the ESMA corpus, are used to automatically assign tonal accent ToBI labels on the (English) Boston Radio news corpus, and vice versa. Using just local raw proso...
متن کاملOn the Alignment of Prosodic Events
The current study examines the relationship between intonational gestures as given by the accent commands of the Fujisaki model and the syllabic grid on the example of spontaneous American English from the Buckeye Corpus. As an initial step the data were labelled according to American English ToBI conventions. Intensity contours were extracted from the band-filtered speech signal and modelled u...
متن کاملToBI accent type recognition
This paper describes work in progress for recognizing a subset of ToBI intonation labels (H*, L+H*, L*, !H*, L+!H*, no accent). Initially, duration characteristics are used to classify syllables as accented or not. The accented syllables are then subclassified based on fundamental frequency, F0, values. Potential F0 intonation gestures are schematized by connected line segments within a window ...
متن کاملA comparison of inter-transcriber reliability for two systems of prosodic annotation: rap (rhythm and pitch) and toBI (tones and break indices)
Agreement was investigated among five labelers for the use of two prosodic annotation systems: the ToBI (Tones and Break Indices) system [1,2] and the RaP (Rhythm and Pitch) system [3]. Each system permits the labeling of pitch accents and two levels of phrasal boundaries; RaP also permits labeling of speech rhythm and distinguishes multiple levels of prominence on syllables. After training wit...
متن کاملA Comparison of Inter - Transcriber Reliab Annotation : RaP ( Rhythm and Pitch ) and
Agreement was investigated among five labelers for the use of two prosodic annotation systems: the ToBI (Tones and Break Indices) system [1,2] and the RaP (Rhythm and Pitch) system [3]. Each system permits the labeling of pitch accents and two levels of phrasal boundaries; RaP also permits labeling of speech rhythm and distinguishes multiple levels of prominence on syllables. After training wit...
متن کامل