A Survey on Punjabi Speech Segmentation into Syllable-Like Units Using Group Delay
نویسندگان
چکیده
This paper describes the best method for automatic segmentation of Punjabi speech. Punjabi is one the most widely used language. Consequently, Punjabi is a syllabic language, so syllables are found to be the best units for the preparation of speech database. Further the automatic segmentation of speech is proved to be the better approach than the manual segmentation. The basic characteristics of the speech can be evaluated by the zero crossing rate and short term energy. Due to local energy fluctuation the STE functions are not reliable for continuous speech. Thus the approach used for the segmentation of speech is by using the negative derivative of Fourier transformations i.e. the Group Delay method. The peaks and valleys are better resolved when the signal is in minimum phase in case of group delay approach. Keywords— Short Term Energy, Zero crossing rate, Automatic speech segmentation, Group delay, Syllable units, Punjabi
منابع مشابه
Automatic Segmentation of Punjabi Speech into Syllable-Like Units using Group Delay A Review
The basic building blocks of a speech segmentation system are its units. Thus it’s an important stage to select appropriate units into which the continuous speech needs to be segmented. The syllable like units is found to be the better representative for Indian languages. Punjabi is the most widely used language, thus this paper describes the automatic segmentation of Punjabi speech into syllab...
متن کاملGROUP DELAY BASED SEGMENTATION OF SPONTANEOUS SPEECH INTO SYLLABLE-LIKE UNITS T.Nagarajan,
In the development of a syllable-centric ASR system, segmentation of the acoustic signal into syllabic units is an important stage. This paper presents a minimum phase group delay based approach to segment spontaneous speech into syllable-like units. Here, three different minimum phase signals are derived from the short term energy functions of three sub-bands of speech signals, as if it were a...
متن کاملA syllable based continuous speech recognizer for Tamil
This paper presents a novel technique for building a syllable based continuous speech recognizer when unannotated transcribed train data is available. We present two different segmentation algorithms to segment the speech and the corresponding text into comparable syllable like units. A group delay based two level segmentation algorithm is proposed to extract accurate syllable units from the sp...
متن کاملA Syllable Based Continuous Sp
This paper presents a novel technique for building a syllable based continuous speech recognizer when unannotated transcribed train data is available. We present two different segmentation algorithms to segment the speech and the corresponding text into comparable syllable like units. A group delay based two level segmentation algorithm is proposed to extract accurate syllable units from the sp...
متن کاملA Syllable Based Continuous Sp
This paper presents a novel technique for building a syllable based continuous speech recognizer when unannotated transcribed train data is available. We present two different segmentation algorithms to segment the speech and the corresponding text into comparable syllable like units. A group delay based two level segmentation algorithm is proposed to extract accurate syllable units from the sp...
متن کامل