论文信息 - Automatic Detection of Prominent Words in

Automatic Detection of Prominent Words in

An experimental research with a goal to automati- cally detect prominent words in Russian speech is presented in this paper. The proposed automatic prominent word detection system could be further used as a module of an automatic speech recognition system or as a tool to highlight prominent words within a speech corpus for unit selection text-to-speech synthesis. The detection procedure is based on the use of prosodic features such as speech signal intensity, fundamental frequency and speech segment duration. A large corpus of Russian speech of over 200 000 running words was used to evaluate the proposed prosodic features and statistical method of speech data processing. The proposed system is speaker-independent and achieves an efficiency of 84.2 %.

Daniil Kocharov | Russian Speech

[1] Shrikanth S. Narayanan,et al. An Acoustic Measure for Word Prominence in Spontaneous Speech , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[2] H. Fletcher,et al. Loudness, its definition, measurement and calculation. , 1933 .

[3] Fabio Tamburini,et al. Automatic prominence identification and prosodic typology , 2005, INTERSPEECH.

[4] Louis ten Bosch,et al. Acoustical features as predictors for prominence in read aloud dutch sentences used in ANN's , 1999, EUROSPEECH.

[5] Daniel Jurafsky,et al. The detection of emphatic words using acoustic and lexical features , 2005, INTERSPEECH.

[6] Daniil Kocharov,et al. A Fully Annotated Corpus of Russian Speech , 2010, LREC.

[7] Julia Hirschberg,et al. Detecting Pitch Accents at the Word, Syllable and Vowel Level , 2009, NAACL.