This paper presents a stochastic model of intonation contours for use in text-to-speech synthesis. The model has two modules, a linguistic module that generates abstract prosodic labels from text, and a phonetic module that generates an F0 curve from the abstract prosodic labels. This model differs from previous work in the abstract prosodic labels used, which can be automatically derived from ...

We present an approach to statistical partof-speech tagging that uses two di erent tagsets, one for its internal and one for its external representation. The internal tagset is used in the underlying Markov model, while the external tagset constitutes the output of the tagger. The internal tagset can be modi ed and optimized to increase tagging accuracy (with respect to the external tagset). We...

In this paper, we explore a text type based scheme of text analysis, through the specific problem of detecting the list text type. This is important because TTS systems that can generate the very distinct F0 contour of lists sound more natural. The presented list detection algorithm uses part-of-speech tags as input, and detects lists by computing the alignment costs of clauses in a sentence. T...

This paper presents a stochastic model of French intonation contours for use in text-to-speech synthesis. The model has two modules, a linguistic module that generates abstract prosodic labels from text, and a phonetic module that generates an F0 curve from the abstract prosodic labels. This model differs from previous work in the abstract prosodic labels used, which can be automatically derive...

We introduce a simple wrapper method that uses off-the-shelf word embedding algorithms to learn task-specific bilingual word embeddings. We use a small dictionary of easily-obtainable task-specific word equivalence classes to produce mixed context-target pairs that we use to train off-the-shelf embedding models. Our model has the advantage that it (a) is independent of the choice of embedding a...

It has been argued that, when learning a first language, babies use a series of small clues to aid recognition and comprehension, and that one of these clues is word length. In this paper we present a statistical part of speech tagger which trains itself solely on the number of letters in each word in a sentence.

This paper describes a variety of methods for inserting phrase boundaries in text. The methods work by ex­ amining the likelihood of a phrase break occurring in a sequence of three part-of-speech tags. The paper explains this basic technique and desribes more sophisticaed vari­ ations using distance probabilities.

In this paper, we first had a overall study of existing POS tag sets for European and Indian languages. Till now, most of the research done on POS tagging is for English. We observed that even though the research on POS tagging for English is done exhaustively, part-of-speech annotation in various research applications is incomparable which is variously due to the variations in tag set definiti...