Sony Interactive Entertainment Inc.

Dolby Laboratories Licensing Corporation

Dolby International Ab

Xiaoyu Liu

Ruxin Chen

Sudha Krishnamurthy

Jaekwon Yoo

Min-Hung Chen

Vivek Kumar

Lakshmish Kaushik

Roy M Fejgin

Zhenhao Ge

Cong Zhou

Jordi Pons Puig

Michael Getty Horgan

Berkan Kadioglu

Santiago Pascual

Paul Holmberg

Xu Li

Described is a method of training a deep-learning-based system for sound source separation. The system comprises a separation stage for frame-wise extraction of representations of sound sources from a representation of an audio signal, and a clustering stage for generating, for each frame, a vector indicative of an assignment permutation of extracted frames of representations of sound sources to respective sound sources. The representation of the audio signal is a waveform-based representation. The separation stage is trained using frame-level permutation invariant training. Further, the clustering stage is trained to generate embedding vectors for the frames of the audio signal that allow to determine estimates of respective assignment permutations between extracted sound signals and labels of sound sources that had been used for the frames. Also described is a method of using the deep-learning-based system for sound source separation.

Frame-level permutation invariant training for source separation

Novel methods and systems for adapting a voice cloning synthesizer for a new speaker using real speech data are disclosed. Utterances from one or more target speakers are parameterized and are used to initialize an embedding vector for use with a voice synthesizer, by means of clustering the utterance data and determining the centroid of the data, using a speaker identification neural network, and/or by finding the closest stored embedded vector to the utterance data.

Systems and methods for adapting human speaker embeddings in speech synthesis

A wake-up word for a digital assistant may be specified by a user to trigger the digital assistant to respond to the wake-up word, with the user providing one or more initial pronunciations of the wake-up word. The wake-up word may be unique, or at least not determined beforehand by a device manufacturer or developer of the digital assistant. The initial pronunciation(s) of the keyword may then be augmented with other potential pronunciations of the wake-up word that might be provided in the future, and those other potential pronunciations may then be pruned down to a threshold number of other potential pronunciations. One or more recordings of the initial pronunciation(s) of the wake-up may then be used to train a phoneme recognizer model to better recognize future instances of the wake-up word being spoken by the user or another person using the initial pronunciation or other potential pronunciations.

Phoneme recognizer customizable keyword spotting system with keyword adaptation

A domain adaptation module is used to optimize a first domain derived from a second domain using respective outputs from respective parallel hidden layers of the domains.

Systems and methods for domain adaptation in neural networks using cross-domain batch normalization

Systems and methods for domain adaptation in neural networks using domain classifier

Automatically recommending sound effects based on visual scenes enables sound engineers during video production of computer simulations, such as movies and video games. This recommendation engine may be accomplished by classifying SFX and using a machine learning engine to output a first of the classified SFX for a first computer simulation based on learned correlations between video attributes of the first computer simulation and the classified SFX.

Video tagging by correlating visual features to sound tags

Growing community of inventors

San Mateo, CA, United States of America

Xiaoyu Liu