paper-with-me

Papers

GraphTTS: graph-to-sequence modelling in neural text-to-speech

2020-03-04 · Aolan Sun, Jianzong Wang, Ning Cheng, Huayi Peng, Zhen Zeng, Jing Xiao

This paper leverages the graph-to-sequence method in neural text-to-speech (GraphTTS), which maps the graph embedding of the input sequence to spectrograms. The graphical inputs consist of node and edge representations constructed from input texts. The encoding of these graphical inputs incorporates syntax information by a GNN encoder module. Besides, applying the encoder of GraphTTS as a graph auxiliary encoder (GAE) can analyse prosody information from the semantic structure of texts. This can remove the manual selection of reference audios process and makes prosody modelling an end-to-end procedure. Experimental analysis shows that GraphTTS outperforms the state-of-the-art sequence-to-sequence models by 0.24 in Mean Opinion Score (MOS). GAE can adjust the pause, ventilation and tones of synthesised audios automatically. This experimental conclusion may give some inspiration to researchers working on improving speech synthesis prosody.

📄 PDF Abstract BibTeX arXiv:2003.01924

Code (0)

등록된 구현이 없습니다.

Tasks

Graph EmbeddingGraph-to-SequenceSpeech Synthesistext-to-speechText to Speech

Similar Papers 제목 키워드 기반

GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis

2020-12-03 · Aolan Sun, Jianzong Wang, Ning Cheng, Huayi Peng 외

This paper introduces a graphical representation approach of prosody boundary (GraphPB) in the task of Chinese speech synthesis, intending to parse the semantic and syntactic relationship of input sequences in a graphica…

DecoderGraph EmbeddingGraph Neural NetworkGraph-to-Sequence+4

Compressive Transformers for Long-Range Sequence Modelling

2019-11-13 · ICLR 2020 1 · Jack W. Rae, Anna Potapenko, Siddhant M. Jayakumar, Timothy P. Lillicrap

We present the Compressive Transformer, an attentive sequence model which compresses past memories for long-range sequence learning. We find the Compressive Transformer obtains state-of-the-art language modelling results…

Language Modelling

M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation

2022-07-03 · Jinming Zhao, Hao Yang, Ehsan Shareghi, Gholamreza Haffari

End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due …

DecoderSpeech-to-TextSpeech-to-Text TranslationTranslation

Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR

2022-03-01 · Xuankai Chang, Niko Moritz, Takaaki Hori, Shinji Watanabe 외

Graph-based temporal classification (GTC), a generalized form of the connectionist temporal classification loss, was recently proposed to improve automatic speech recognition (ASR) systems using graph-based supervision. …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Pseudo Labelspeech-recognition+1

MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions

2023-02-23 · Shengkui Zhao, Bin Ma

Transformer based models have provided significant performance improvements in monaural speech separation. However, there is still a performance gap compared to a recent proposed upper bound. The major limitation of the …

Speech Separation