Deprecated: mysql_connect(): The mysql extension is deprecated and will be removed in the future: use mysqli or PDO instead in /home/freehos1/public_html/projectus/core/open_close_dbase_connection.php on line 0

Deprecated: Function split() is deprecated in /home/freehos1/public_html/projectus/Pitch-detection/index.php(0) : eval()'d code on line 22

Deprecated: Function split() is deprecated in /home/freehos1/public_html/projectus/Pitch-detection/index.php(0) : eval()'d code on line 35

Deprecated: mysql_connect(): The mysql extension is deprecated and will be removed in the future: use mysqli or PDO instead in /home/freehos1/public_html/projectus/scripts/get_ad_type_position.php on line 0

Deprecated: mysql_connect(): The mysql extension is deprecated and will be removed in the future: use mysqli or PDO instead in /home/freehos1/public_html/projectus/scripts/load_ads.php on line 0

Deprecated: mysql_connect(): The mysql extension is deprecated and will be removed in the future: use mysqli or PDO instead in /home/freehos1/public_html/projectus/scripts/sponsor_found.php on line 0

Deprecated: mysql_connect(): The mysql extension is deprecated and will be removed in the future: use mysqli or PDO instead in /home/freehos1/public_html/projectus/scripts/load_links.php on line 0

Deprecated: Function split() is deprecated in /home/freehos1/public_html/projectus/Pitch-detection/index.php(0) : eval()'d code on line 161

Deprecated: Function split() is deprecated in /home/freehos1/public_html/projectus/Pitch-detection/index.php(0) : eval()'d code on line 164

Deprecated: Function split() is deprecated in /home/freehos1/public_html/projectus/Pitch-detection/index.php(0) : eval()'d code on line 167
tone recognition
projectus.freehost7.com:UG and PG level projects,mini projects and many more here ...



 

 

 

Tone recognition for Mandarin Chinese [11]

 

 

Tone identification is essential for the recognition of the Chinese language, specifically far Cantonese which is well known for being very rich in tones. Most cues for Mandarin tone recognition involve pitch, overall intensity and duration. The automatic recognition of tones in Mandarin is a difficult problem that is being approached from several directions. Approaches include correcting for co articulation and phrase-level declination, and using better machine learning techniques. Pitch is the obvious cue for tone recognition, while (overall) intensity and durational features also play a role. We fixed a dataset of news broadcast Mandarin speech, a classification algorithm, and a set of core features involving pitch, overall intensity and duration. We then found the change in classification accuracy when the core features were augmented with features from a variety of other cues.  Suprasegmental feature parameters are extracted from the voiced portion of a monosyllabic utterance and a three-layer feed forward neural network is used to classify these feature vectors. Using a phonologically complete vocabulary of 234 distinct syllables, the recognition accuracy for single-speaker and multi speaker is given by 89.0% and 87.6% respectively