Group delay based phone segmentation for HTS

Abstract

HMM based speech synthesis (HTS) is a state-ofthe art approach to text-to-speech synthesis. Segmentation of the training data is essential for building any text-to-speech system. Most conventional text-to-speech systems use phones as the basic unit of synthesis and use a speech recogniser to automatically segment the data at the phone level. As Indian languages are low resource languages, accurate transcriptions are difficult to obtain owing to paucity of data. Manual labeling at the phone level is not only laborious but also inaccurate. HMM based flat start segmentation doesn't work well at the sentence level. In this paper we propose an event driven approach to obtain better phone boundaries. Syllable-like events are detected in the speech signal and matched with syllabified transcription of the text. The syllables are converted to phoneme sequences and Baum-Welch embedded re-estimation is restricted to the syllable-level. Subjective evaluations indicate that the proposed system has a lower word error rate compared to that of a conventional system that uses flat start for obtaining phone boundaries.

Building speech synthesis systems for Indian languages

“…Embedded re-estimation is performed between a pair of conect boundaries. This results in better phone segmentation and syllable segmentation [30], [31]. Figure 2 illustrates the proposed approach.…”

Akshara transcription of mrudangam strokes in Carnatic music

“…There are many composite aksharas in mrudangam, which makes the list of unique aksharas very large as shown in Table II 2) Onset Detection: Using onset detection, the starting of all aksharas are recognized. The onset detection is performed using the group delay algorithm [2] [15], where the akshara sequence signal is processed similar to that of syllables in 3) Feature Extraction: Mel-frequency cepstral co-efficients (MFCC) features are extracted using the HTK toolkit [16]. The frame size is 20 msec and the frame shift is 2 msec.…”