1 |
Building Robust Spoken Language Understanding by Cross Attention between Phoneme Sequence and ASR Hypothesis ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis ...
|
|
|
|
Abstract:
Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which makes it challenging when converting a paragraph of texts into natural and expressive speech. In this paper, we propose to use the text embeddings of the neighboring sentences to improve the prosody generation for each utterance of a paragraph in an end-to-end fashion without using any explicit prosody features. More specifically, cross-utterance (CU) context vectors, which are produced by an additional CU encoder based on the sentence embeddings extracted by a pre-trained BERT model, are used to augment the input of the Tacotron2 decoder. Two types of BERT embeddings are investigated, which leads to the use of different CU encoder structures. Experimental results on a Mandarin audiobook dataset and the LJ-Speech English audiobook dataset demonstrate the use of CU information can improve the naturalness and expressiveness of the ... : 5 pages, 4 figures ...
|
|
Keyword:
Audio and Speech Processing eess.AS; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Machine Learning cs.LG; Sound cs.SD
|
|
URL: https://arxiv.org/abs/2011.05161 https://dx.doi.org/10.48550/arxiv.2011.05161
|
|
BASE
|
|
Hide details
|
|
4 |
Question-Answering with Grammatically-Interpretable Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Language Models for Image Captioning: The Quirks and What Works ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
A NEW HYBRID STRUCTURE OF SPEECH RECOGNIZER BASED ON HMM AND NEURAL NETWORK
|
|
|
|
In: http://research.microsoft.com/%7Exiaohe/publication/euro99zhou_pap.pdf
|
|
BASE
|
|
Show details
|
|
|
|