Pronunciation Dictionary-Free Multilingual Speech Synthesis by Combining Unsupervised and Supervised Phonetic Representations
This paper proposes a multilingual speech synthesis method which combines unsupervised phonetic representations (UPR) and supervised phonetic representations (SPR) to avoid reliance on the pronunciation dictionaries of target languages. In this method, a pretrained wav2vec 2.0 model is adopted to extract UPRs and a language-independent automatic speech recognition (LI-ASR) model is built with a connectionist temporal classification (CTC) loss to extract segment-level SPRs from the audio data of target languages. Then, an acoustic model is designed, which first predicts UPRs and SPRs from texts separately and then combines the predicted UPRs and SPRs to generate mel-spectrograms. The results of our experiments on six languages show that the proposed method outperformed the methods that directly predicted mel-spectrograms from character or phoneme sequences and the ablated models that utilized only UPRs or SPRs.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSpeech SynthesisSimilar Papers 제목 키워드 기반
Decoupled Pronunciation and Prosody Modeling in Meta-Learning-Based Multilingual Speech Synthesis
This paper presents a method of decoupled pronunciation and prosody modeling to improve the performance of meta-learning-based multilingual speech synthesis. The baseline meta-learning synthesis method adopts a single te…
DecoderMeta-LearningSpeech SynthesisGlobalPhone: Pronunciation Dictionaries in 20 Languages
This paper describes the advances in the multilingual text and speech database GlobalPhone, a multilingual database of high-quality read speech with corresponding transcriptions and pronunciation dictionaries in 20 langu…
Language IdentificationLanguage ModellingSpeaker Recognitionspeech-recognition+2Learning pronunciation from a foreign language in speech synthesis networks
Although there are more than 6,500 languages in the world, the pronunciations of many phonemes sound similar across the languages. When people learn a foreign language, their pronunciation often reflects their native lan…
Speech SynthesisThe Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech
We compare phone labels and articulatory features as input for cross-lingual transfer learning in text-to-speech (TTS) for low-resource languages (LRLs). Experiments with FastSpeech 2 and the LRL West Frisian show that u…
Cross-Lingual Transfertext-to-speechText to SpeechTransfer LearningDNN-Based Multilingual Automatic Speech Recognition for Wolaytta using Oromo Speech
It is known that Automatic Speech Recognition (ASR) is very useful for human-computer interaction in all the human languages. However, due to its requirement for a big speech corpus, which is very expensive, it has not b…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling+2