paper-with-me

홈 › Papers

Prosody Labelled Dataset for Hindi

2021-12-01 · SMP (ICON) 2021 12 · Esha Banerjee, Atul Kr. Ojha, Girish Jha

This study aims to develop an intonation labelled database for Hindi, for enhancing prosody 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 intonational theories in Hindi, this study attempts to develop a manually annotated prosodic corpus of Hindi speech data, which can be used for training speech models for natural-sounding speech in the future. 500 sentences (2,550 words) for declarative and interrogative types have been labelled using Praat.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Prosody Labelled Dataset for Hindi using Semi-Automated Approach

2021-12-11 · Esha Banerjee, Atul Kr. Ojha, Girish Nath Jha

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 …

Machine TranslationTranslation

A Systematic Review of Hindi Prosody

2017-05-09 · Somnath Roy

Prosody describes both form and function of a sentence using the suprasegmental features of speech. Prosody phenomena are explored in the domain of higher phonological constituents such as word, phonological phrase and i…

Sentence

Deriving Word Prosody from Orthography in Hindi

2017-12-01 · WS 2017 12 · Somnath Roy

Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Sparsity

2016-12-01 · WS 2016 12 · Vinayak Athavale, Shreenivas Bharadwaj, Monik Pamecha, Ameya Prabhu 외
Feature EngineeringMachine TranslationMorphological AnalysisNamed Entity Recognition (NER)+2

Disentangling Prosody Representations with Unsupervised Speech Reconstruction

2022-12-14 · Leyuan Qu, Taihao Li, Cornelius Weber, Theresa Pekarek-Rosin 외

Human speech can be characterized by different components, including semantic content, speaker identity and prosodic information. Significant progress has been made in disentangling representations for semantic content a…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DisentanglementEmotion Recognition+6