Extending the vocabulary of a large vocabulary speech recognition system usually requires phonetic transcriptions for all words to be known. With automatic phonetic baseform determination acoustic samples of the words in question can substitute for the required expert knowledge. In this paper we follow a probabilitistic approach to this problem and present a novel breadth-first search algorithm...

Linguistic knowledge has been maligned by speech recognition researchers in the past as being harmful to good performance. However an examination of the advances in speech recognition and speech synthesis shows that many of them were made by incorporating linguistic knowledge into the systems. The most useful type of knowledge is of a quantitative, rather that qualitative nature. This is precis...

Automatic phonetic transcription tools usually perform phonetic transcriptions directly from orthographic representations. Although these approaches often achieve good results, theoretical studies suggest that including morphophonological knowledge allows those systems to improve their performance. Following this idea, we developed a tool which first obtains an underlying representation of each...

Automatic dialect identification, like automatic language identification , has often been approached through the use of phonetic frequencies and phonetic sequence modeling. While such statistical systems perform well on language identification problems, they are less adept at the more difficult problem of automatic dialect identification, particularly on short segments of speech. In this paper ...

The demand and the importance of Chinese teaching have increased continuously. In order to assist the Chinese learners in composing Chinese characters and increase their learning efficiency, Chinese components teaching method is adopted. The learners can find the clues to both the pronunciations and the meanings of Chinese characters from Chinese components, and semantic-phonetic compounds and ...

Phone recognition experiments give information about the confusions between phones. Grouping the most confusable phones and making a multilevel hierarchical classification should improve phone recognition. In this paper a clustering method is investigated, based on phone confusion matrix, for the data-driven generation of phonetic broad classes (PBC) of the Portuguese language. The method is ba...

A multivariate-state HMM | an HMM with a vector state variable | can be used to nd jointly optimal phonetic and formant transcriptions of an utterance. The complexity of searching a multivariate state space using the BaumWelch algorithm is substantial, but may be signi cantly reduced if the formant frequencies are assumed to be conditionally independent given knowledge of the phone. Operating w...

A multivariat,e-state HMM an HMM with a vector state variable can be used to find jointly optimal phonetic and formant transcriptions of an utterance. The complexity of searching a multivariate state space using the BaumWelch algorithm is substantial, but may be significantly reduced if the formant frequencies are assumed to be conditionally independent given knowledge of the phone. Operating w...

Many listener-oriented theories of phonetic reduction assume that the talker has tacit knowledge of an interlocutor’s mental state, and consequently predict that talkers with poor theory of mind should exhibit inconsistent behavior between semantic contexts. This study examined effects of individual differences in theory of mind skills on extent of phonetic reduction in three acoustic domains (...

Correct and temporally accurate phonetic segmentation of speech utterances is important in applications ranging from transcription alignment to pronunciation error detection. Automatic speech recognizers used in these tasks provide insufficient temporal alignment accuracy apart from a recognition performance that is sensitive to accent and style variations from the training data. A two-staged a...