paper-with-me

Papers

FBWave: Efficient and Scalable Neural Vocoders for Streaming Text-To-Speech on the Edge

2020-11-25 · Bichen Wu, Qing He, Peizhao Zhang, Thilo Koehler, Kurt Keutzer, Peter Vajda

Nowadays more and more applications can benefit from edge-based text-to-speech (TTS). However, most existing TTS models are too computationally expensive and are not flexible enough to be deployed on the diverse variety of edge devices with their equally diverse computational capacities. To address this, we propose FBWave, a family of efficient and scalable neural vocoders that can achieve optimal performance-efficiency trade-offs for different edge devices. FBWave is a hybrid flow-based generative model that combines the advantages of autoregressive and non-autoregressive models. It produces high quality audio and supports streaming during inference while remaining highly computationally efficient. Our experiments show that FBWave can achieve similar audio quality to WaveRNN while reducing MACs by 40x. More efficient variants of FBWave can achieve up to 109x fewer MACs while still delivering acceptable audio quality. Audio demos are available at https://bichenwu09.github.io/vocoder_demos.

📄 PDF Abstract BibTeX arXiv:2011.12985

Code (0)

등록된 구현이 없습니다.

Tasks

text-to-speechText to Speech

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
WaveRNN WaveRNN is a single-layer recurrent neural network for audio generation that is designed efficiently predict 16-bit raw audio samples. The overall computation in the…

Similar Papers 제목 키워드 기반

A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate

2021-08-09 · Ahmed Mustafa, Jan Büthe, Srikanth Korse, Kishan Gupta 외

Recently, GAN vocoders have seen rapid progress in speech synthesis, starting to outperform autoregressive models in perceptual quality with much higher generation speed. However, autoregressive vocoders are still the co…

Speech Synthesis

Towards Robust Neural Vocoding for Speech Generation: A Survey

2019-12-05 · Po-chun Hsu, Chun-hsuan Wang, Andy T. Liu, Hung-Yi Lee

Recently, neural vocoders have been widely used in speech synthesis tasks, including text-to-speech and voice conversion. However, when encountering data distribution mismatch between training and inference, neural vocod…

Speech SynthesisSurveytext-to-speechText to Speech+1

Parallel Neural Text-to-Speech

2020-01-01 · ICLR 2020 1 · Kainan Peng, Wei Ping, Zhao Song, Kexin Zhao

In this work, we first propose ParaNet, a non-autoregressive seq2seq model that converts text to spectrogram. It is fully convolutional and obtains 46.7 times speed-up over Deep Voice 3 at synthesis while maintaining com…

text-to-speechText to Speech

Speaker independence of neural vocoders and their effect on parametric resynthesis speech enhancement

2019-11-14 · Soumi Maiti, Michael I Mandel

Traditional speech enhancement systems produce speech with compromised quality. Here we propose to use the high quality speech generation capability of neural vocoders for better quality speech enhancement. We term this …

ResynthesisSpeech Enhancement

Speaker-adaptive neural vocoders for parametric speech synthesis systems

2018-11-08 · Eunwoo Song, Jin-Seob Kim, Kyungguen Byun, Hong-Goo Kang

This paper proposes speaker-adaptive neural vocoders for parametric text-to-speech (TTS) systems. Recently proposed WaveNet-based neural vocoding systems successfully generate a time sequence of speech signal with an aut…

Speech Synthesistext-to-speechText to Speech