Title :
Formant-based technique for automatic filled-pause detection in spontaneous spoken english
Author :
Audhkhasi, Kartik ; Kandhway, Kundan ; Deshmukh, Om D. ; Verma, Ashish
Author_Institution :
Dept of Electr. Eng., Univ of Southern California, Los Angeles, CA
Abstract :
Detection of filled pauses is a challenging research problem which has several practical applications. It can be used to evaluate the spoken fluency skills of the speaker, to improve the performance of automatic speech recognition systems or to predict the mental state of the speaker. This paper presents an algorithm for filled pause detection that is based on the premise that the vocal tract characteristics, and hence the formants, are stable during the production of a filled pause. The performance of the proposed algorithm is evaluated on real-life recordings of call center agents where the locations of the filled pauses are hand labeled. The proposed algorithm outperforms a standard cepstral stability based filled pause detection algorithm and a standard pitch-based detection technique.
Keywords :
cepstral analysis; natural language processing; signal detection; speaker recognition; automatic filled-pause detection; automatic speech recognition system; call center agent; cepstral stability; formant-based technique; spontaneous spoken English; standard pitch-based detection technique; vocal tract characteristics; Acoustic measurements; Acoustic signal detection; Automatic speech recognition; Cepstral analysis; Databases; Detection algorithms; Frequency; Gravity; Natural languages; Robust stability; Filled pause; fluency evaluation; spectral features; vowel lengthening;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-2353-8
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2009.4960719