Abstract :
The following topics are dealt with: dysarthric speech database; speech assessments; linguistics-oriented language resource development; Hindi speech; Lacito multimedia archive; phonotactic aspect; AESOP; Asian English speech corpus project; Hindi mobile communication text; Hindi mobile communication speech corpus; QoLT software technology; Bengali speech corpus; continuous automatic speech recognition system; declarative utterances; interrogative utterances; Chinese EFL learners; American native speakers; Chinese intonation transcription; Shandong dialect influence; Internet-accessible computer-aided pronunciation training system; adaptive noise estimation; adaptive noise reduction; two-stage Wiener filtering; question-and-answer classification technique; spoken dialog system construction; feature normalization; feature selection; unsupervised spoken term detection; acoustic segment model; morpheme concatenation approach; language modeling; speech technology role; Chinese-English code-switching speech database; acoustic parameter database; text-to-speech development; turn management modeling; multiaccent Mandarin corpus; unsupervised phone segmentation method; interactive visualization system; interactive search system; acoustic signal dictionary creation; Japanese response token annotation; Malay emotional voice corpora naturalness; Uigur vowel acoustic feature; and Uigur vowel acoustic variance.
Keywords :
Internet; Wiener filters; acoustic signal processing; computer based training; data visualisation; mobile communication; multimedia communication; multimedia databases; natural language processing; question answering (information retrieval); signal denoising; speech recognition; speech synthesis; text analysis; AESOP; American native speakers; Asian English speech corpus project; Bengali speech corpus; Chinese EFL learners; Chinese intonation transcription; Chinese-English code-switching speech database; Hindi mobile communication speech corpus; Hindi mobile communication text; Hindi speech; Internet-accessible computer-aided pronunciation training system; Japanese response token annotation; Lacito multimedia archive; Malay emotional voice corpora naturalness; QoLT software technology; Shandong dialect influence; Uigur vowel acoustic feature; Uigur vowel acoustic variance; acoustic parameter database; acoustic segment model; acoustic signal dictionary creation; adaptive noise estimation; adaptive noise reduction; continuous automatic speech recognition system; declarative utterances; dysarthric speech database; feature normalization; feature selection; interactive search system; interactive visualization system; interrogative utterances; language modeling; linguistics-oriented language resource development; morpheme concatenation approach; multiaccent Mandarin corpus; phonotactic aspect; question-and-answer classification technique; speech assessments; speech technology role; spoken dialog system construction; text-to-speech development; turn management modeling; two-stage Wiener filtering; unsupervised phone segmentation method; unsupervised spoken term detection;
Conference_Titel :
Speech Database and Assessments (Oriental COCOSDA), 2011 International Conference on
Conference_Location :
Hsinchu
Print_ISBN :
978-1-4577-0930-2
DOI :
10.1109/ICSDA.2011.6086118
