arXiv subjects

Sercan O. Arik

Publications and source records attributed to Sercan O. Arik.

41 records · Page 3Linked to original sources

arXiv2018

Neural Voice Cloning with a Few Samples

Voice cloning is a highly desired feature for personalized speech interfaces. Neural network based speech synthesis has been shown to generate high quality speech for a large number of speakers. In this paper, we introduce a neural voice cloning system that takes a few audio samples as input. We study two approaches: speaker adaptation and speaker encoding. Speaker adaptation is based on fine-tuning a multi-speaker generative model with a few cloning samples. Speaker encoding is based on training a separate model to directly infer a new speaker embedding from cloning audios and to be used with a multi-speaker generative model. In terms of naturalness of the speech and its similarity to original speaker, both approaches can achieve good performance, even with very few cloning audios. While speaker adaptation can achieve better naturalness and similarity, the cloning time or required memory for the speaker encoding approach is significantly less, making it favorable for low-resource deployment.

cs.CL↗

arXiv2018

Low-complexity implementation of convex optimization-based phase retrieval

Phase retrieval has important applications in optical imaging, communications and sensing. Lifting the dimensionality of the problem allows phase retrieval to be approximated as a convex optimization problem in a higher-dimensional space. Convex optimization-based phase retrieval has been shown to yield high accuracy, yet its low-complexity implementation has not been explored. In this paper, we study three fundamental approaches for its low-complexity implementation: the projected gradient method, the Nesterov accelerated gradient method, and the alternating direction method of multipliers (ADMM) method. We derive the corresponding estimation algorithms and evaluate their complexities. We compare their performance in the application area of direct-detection mode-division multiplexing. We demonstrate that they yield negligible estimation penalties (less than 0.2 dB for transmitter processing and less than 0.6 dB for receiver equalization) while yielding low computational cost, as their implementation complexities all scale quadratically in the number of unknown parameters. Among the three methods, ADMM achieves convergence after the smallest number of iterations.

cs.IT↗

arXiv2018

Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning

We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS) system. Deep Voice 3 matches state-of-the-art neural speech synthesis systems in naturalness while training ten times faster. We scale Deep Voice 3 to data set sizes unprecedented for TTS, training on more than eight hundred hours of audio from over two thousand speakers. In addition, we identify common error modes of attention-based speech synthesis networks, demonstrate how to mitigate them, and compare several different waveform synthesis methods. We also describe how to scale inference to ten million queries per day on one single-GPU server.

cs.SD↗

arXiv2017

Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting

Keyword spotting (KWS) constitutes a major component of human-technology interfaces. Maximizing the detection accuracy at a low false alarm (FA) rate, while minimizing the footprint size, latency and complexity are the goals for KWS. Towards achieving them, we study Convolutional Recurrent Neural Networks (CRNNs). Inspired by large-scale state-of-the-art speech recognition systems, we combine the strengths of convolutional layers and recurrent layers to exploit local structure and long-range context. We analyze the effect of architecture parameters, and propose training strategies to improve performance. With only ~230k parameters, our CRNN model yields acceptably low latency, and achieves 97.71% accuracy at 0.5 FA/hour for 5 dB signal-to-noise ratio.

cs.CL↗

arXiv2017

Deep Voice: Real-time Neural Text-to-Speech

We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks. Deep Voice lays the groundwork for truly end-to-end neural speech synthesis. The system comprises five major building blocks: a segmentation model for locating phoneme boundaries, a grapheme-to-phoneme conversion model, a phoneme duration prediction model, a fundamental frequency prediction model, and an audio synthesis model. For the segmentation model, we propose a novel way of performing phoneme boundary detection with deep neural networks using connectionist temporal classification (CTC) loss. For the audio synthesis model, we implement a variant of WaveNet that requires fewer parameters and trains faster than the original. By using a neural network for each component, our system is simpler and more flexible than traditional text-to-speech systems, where each component requires laborious feature engineering and extensive domain expertise. Finally, we show that inference with our system can be performed faster than real time and describe optimized WaveNet inference kernels on both CPU and GPU that achieve up to 400x speedups over existing implementations.

cs.CL↗