paper-with-me

홈 › Papers

Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis

2018-07-18 · Jing-Xuan Zhang, Zhen-Hua Ling, Li-Rong Dai

This paper proposes a forward attention method for the sequenceto- sequence acoustic modeling of speech synthesis. This method is motivated by the nature of the monotonic alignment from phone sequences to acoustic sequences. Only the alignment paths that satisfy the monotonic condition are taken into consideration at each decoder timestep. The modified attention probabilities at each timestep are computed recursively using a forward algorithm. A transition agent for forward attention is further proposed, which helps the attention mechanism to make decisions whether to move forward or stay at each decoder timestep. Experimental results show that the proposed forward attention method achieves faster convergence speed and higher stability than the baseline attention method. Besides, the method of forward attention with transition agent can also help improve the naturalness of synthetic speech and control the speed of synthetic speech effectively.

📄 PDF Abstract BibTeX arXiv:1807.06736

Code (0)

등록된 구현이 없습니다.

Tasks

Acoustic ModellingDecoderSpeech Synthesis

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer

2019-10-22 · Merlijn Blaauw, Jordi Bonada

We propose a sequence-to-sequence singing synthesizer, which avoids the need for training data with pre-aligned phonetic and acoustic features. Rather than the more common approach of a content-based attention mechanism …

Decoder

End-to-End Attention-based Large Vocabulary Speech Recognition

2015-08-18 · Dzmitry Bahdanau, Jan Chorowski, Dmitriy Serdyuk, Philemon Brakel 외

Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs). Most of these systems contain separate components that d…

Acoustic ModellingLanguage ModelingLanguage Modellingspeech-recognition+1

Acoustic-to-Word Recognition with Sequence-to-Sequence Models

2018-07-23 · Shruti Palaskar, Florian Metze

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solu…

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

OverFlow: Putting flows on top of neural transducers for better TTS

2022-11-13 · Shivam Mehta, Ambika Kirkland, Harm Lameris, Jonas Beskow 외

Neural HMMs are a type of neural transducer recently proposed for sequence-to-sequence modelling in text-to-speech. They combine the best features of classic statistical speech synthesis and modern neural TTS, requiring …

Normalising FlowsSpeech Synthesistext-to-speechText to Speech+1

Deep Recurrent Neural Networks for Acoustic Modelling

2015-04-07 · William Chan, Ian Lane

We present a novel deep Recurrent Neural Network (RNN) model for acoustic modelling in Automatic Speech Recognition (ASR). We term our contribution as a TC-DNN-BLSTM-DNN model, the model combines a Deep Neural Network (D…

Acoustic ModellingAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognition+1