Record speech signal of a sentence in any of the Indian languages, identify and mark by listening, manually, the boundaries of words and subword units (such as syllables and phonemes). Draw on a piece of paper the speech waveform for the first few words of the sentence with appropriate time durations and relative amplitudes of various sounds, clearly marking the various subword boundaries.
The main objective of this experiment is to make the student understand and appreciate the difficulties in automating the task of speech signal-to-symbol transformation. The students are expected to understand terms such as phones, phonemes, syllables, transliteration, pitch or fundamental frequency, quasi-periodicity. The student should gain a good understanding of the speech signal by visual inspection. Given a speech waveform one should be able to discriminate between silence and speech, voiced speech and unvoiced speech. The student should be able to draw the speech waveform for a given word with appropriate time durations and relative amplitudes of the constituent phones.
1.Visualization of speech
- Record the speech signal for the above chosen sentence
- Display a speech file using the utility ”wavesurfer”.
- Learn to discriminate visually between silence and speech by looking at the signal, by repeatedly zooming, selecting and playing various portions of the recorded signal.
2.Choice of symbols
Write down a sentence in Indian language using the native Indian script
- Transliterate or write the same sentence in English
- Transliterate the sentence in English using ITRANS code
- Break down the word-level transcription into syllables and phonemes
3.Segmentation of speech
- Identify and mark the beginning and ending of the words in the sentence. Make a note of the durations of these words.
- Identify and mark the boundaries of syllables within each word and note down the durations.
- Identify and mark the phoneme boundaries within each syllable and note down the durations.
4.Sketching the speech waveform
- Observe carefully the change in amplitude and structure of the signal for different sounds or phonemes.
- Now draw the waveform of the speech signal on paper for the first four words in the sentence marking all the word, syllable and phoneme boundaries. Use a rough scale of [5 cm = 100 ms].
- Repeat the same procedure for another utterance in the same language or a different language, and for the same speaker or a different speaker.
5.Write a brief report on your observations.