Baidu USA LLC

Yanqi Zhou

Sercan Omer Arik

Gregory Diamos

Wei Ping

Kainan Peng

Andrew Gibiansky

John Miller

Jonathan Raiman

Haonan Yu

Hairong Liu

Hee Woo Jun

Joel Hestness

Jitong Chen

Sharan Narang

Siavash Ebrahimi

Newsha Ardalani

Md Mostofa Ali Patwary

Neural Architecture Search (NAS) is a laborious process. Prior work on automated NAS targets mainly on improving accuracy but lacked consideration of computational resource use. Presented herein are embodiments of a Resource-Efficient Neural Architect (RENA), an efficient resource-constrained NAS using reinforcement learning with network embedding. RENA embodiments use a policy network to process the network embeddings to generate new configurations. Example demonstrates of RENA embodiments on image recognition and keyword spotting (KWS) problems are also presented herein. RENA embodiments can find novel architectures that achieve high performance even with tight resource constraints. For the CIFAR10 dataset, the tested embodiment achieved 2.95% test error when compute intensity is greater than 100 FLOPs/byte, and 3.87% test error when model size was less than 3M parameters. For the Google Speech Commands Dataset, the tested RENA embodiment achieved the state-of-the-art accuracy without resource constraints, and it outperformed the optimized architectures with tight resource constraints.

Resource-efficient neural architects

Described herein are systems and methods for augmenting neural speech synthesis networks with low-dimensional trainable speaker embeddings in order to generate speech from different voices from a single model. As a starting point for multi-speaker experiments, improved single-speaker model embodiments, which may be referred to generally as Deep Voice 2 embodiments, were developed, as well as a post-processing neural vocoder for Tacotron (a neural character-to-spectrogram model). New techniques for multi-speaker speech synthesis were performed for both Deep Voice 2 and Tacotron embodiments on two multi-speaker TTS datasets&#x2014;showing that neural text-to-speech systems can learn hundreds of unique voices from twenty-five minutes of audio per speaker.

Multi-speaker neural text-to-speech

As deep learning application domains grow, a deeper understanding of the relationships between training set size, computational scale, and model accuracy improvements is extremely beneficial. Presented herein are large-scale empirical study of error and model size growth as training sets grow. Embodiments of a methodology for this measurement are introduced herein as well as embodiments for predicting other metrics, such as compute-related metrics. It is shown herein that power-law may be used to represent deep model relationships, such as error and training data size. It is also shown that model size scales sublinearly with data size. These scaling relationships have significant implications on deep learning research, practice, and systems. They can assist model debugging, setting accuracy targets, and decisions about data set growth. They can also guide computing system design and underscore the importance of continued computational scaling.

Predicting deep learning scaling

Voice cloning is a highly desired capability for personalized speech interfaces. Neural network-based speech synthesis has been shown to generate high quality speech for a large number of speakers. Neural voice cloning systems that take a few audio samples as input are presented herein. Two approaches, speaker adaptation and speaker encoding, are disclosed. Speaker adaptation embodiments are based on fine-tuning a multi-speaker generative model with a few cloning samples. Speaker encoding embodiments are based on training a separate model to directly infer a new speaker embedding from cloning audios, which is used in or with a multi-speaker generative model. Both approaches achieve good performance in terms of naturalness of the speech and its similarity to original speaker&#x2014;even with very few cloning audios.

Systems and methods for neural voice cloning with a few samples

Systems and methods for multi-speaker neural text-to-speech

Growing community of inventors

San Jose, CA, United States of America

Yanqi Zhou