Prosody Labelled Dataset for Hindi using Semi-Automated Approach
It addresses the lack of standardized prosody resources for Hindi, which is incremental as it builds on existing theories and methods.
This study developed a semi-automatically labelled prosody dataset for Hindi to improve intonation in ASR and TTS systems, achieving model accuracies of 73.40% for pitch accent, 93.20% for intermediate phrase boundaries, and 43% for accentual phrase boundaries on 5,000 sentences.
This study aims to develop a semi-automatically labelled prosody database for Hindi, for enhancing the intonation component in ASR and TTS systems, which is also helpful for building Speech to Speech Machine Translation systems. Although no single standard for prosody labelling exists in Hindi, researchers in the past have employed perceptual and statistical methods in literature to draw inferences about the behaviour of prosody patterns in Hindi. Based on such existing research and largely agreed upon theories of intonation in Hindi, this study attempts to first develop a manually annotated prosodic corpus of Hindi speech data, which is then used for training prediction models for generating automatic prosodic labels. A total of 5,000 sentences (23,500 words) for declarative and interrogative types have been labelled. The accuracy of the trained models for pitch accent, intermediate phrase boundaries and accentual phrase boundaries is 73.40%, 93.20%, and 43% respectively.