An Investigation of the Relation Between Grapheme Embeddings and Pronunciation for Tacotron-based Systems
End-to-end models, particularly Tacotron-based ones, are currently a popular solution for text-to-speech synthesis. They allow the production of high-quality synthesized speech with little to no text preprocessing. Indeed, they can be trained using either graphemes or phonemes as input directly. However, in the case of grapheme inputs, little is known concerning the relation between the underlying representations learned by the model and word pronunciations. This work investigates this relation in the case of a Tacotron model trained on French graphemes. Our analysis shows that grapheme embeddings are related to phoneme information despite no such information being present during training. Thanks to this property, we show that grapheme embeddings learned by Tacotron models can be useful for tasks such as grapheme-to-phoneme conversion and control of the pronunciation in synthetic speech.
Code (0)
등록된 구현이 없습니다.
Tasks
Grapheme-to-Phoneme ConversionRelationSpeech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Low-Resource Machine Transliteration Using Recurrent Neural Networks of Asian Languages
Grapheme-to-phoneme models are key components in automatic speech recognition and text-to-speech systems. With low-resource language pairs that do not have available and well-developed pronunciation lexicons, grapheme-to…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognition+6Multimodal neural pronunciation modeling for spoken languages with logographic origin
Graphemes of most languages encode pronunciation, though some are more explicit than others. Languages like Spanish have a straightforward mapping between its graphemes and phonemes, while this mapping is more convoluted…
No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models
For decades, context-dependent phonemes have been the dominant sub-word unit for conventional acoustic modeling systems. This status quo has begun to be challenged recently by end-to-end models which seek to combine acou…
Language ModelingLanguage ModellingLearning to pronounce as measuring cross-lingual joint orthography-phonology complexity
Machine learning models allow us to compare languages by showing how hard a task in each language might be to learn and perform well on. Following this line of investigation, we explore what makes a language "hard to pro…
TransliterationA systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models
Following the rationale of end-to-end modeling, CTC, RNN-T or encoder-decoder-attention models for automatic speech recognition (ASR) use graphemes or grapheme-based subword units based on e.g. byte-pair encoding (BPE). …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognition+1