Google Inc.

Marco Tagliasacchi

Dominik Roblek

Neil Zeghidour

Beat Gfeller

Zalán Borsos

Matthew Nirvan Sharifi

Christian Frank

Félix De Chaumont Quitry

Jesse Engel

Adam Roberts

Timo Immanuel Denk

Andrea Agostinelli

Antoine Caillon

Mauro Verzetti

Rajeev Conrad Nongpiur

Aren Jansen

Sze Chie Lim

Qian Zhang

Kevin I Kilgour

Leonardo Kusumo

David G Grangier

Karolis Misiunas

Hannah Muckenhirn

Scott Wisdom

Hélène Bahu

Mihajlo Velimirovic

Michael Takezo Chinen

Kung-Wei Liu

Qingqing Huang

Yunpeng Li

Olivier Teboul

Jihan Li

Andrew James Sutter

Oleg Rybakov

Victor Ungureanu

Raphaël Marinier

Example methods include receiving training data comprising a plurality of audio clips and a plurality of textual descriptions of audio. The methods include generating a shared representation comprising a joint embedding. An audio embedding of a given audio clip is within a threshold distance of a text embedding of a textual description of the given audio clip. The methods include generating, based on the joint embedding, a conditioning vector and training, based on the conditioning vector, a neural network to: receive (i) an input audio waveform, and (ii) an input comprising one or more of an input textual description of a target audio source in the input audio waveform, or an audio sample of the target audio source, separate audio corresponding to the target audio source from the input audio waveform, and output the separated audio corresponding to the target audio source in response to the receiving of the input.

Conditioned separation of arbitrary sounds based on machine learning models

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a prediction of an audio signal. One of the methods includes receiving a request to generate an audio signal conditioned on an input; processing the input using an embedding neural network to map the input to one or more embedding tokens; generating a semantic representation of the audio signal; generating, using one or more generative neural networks and conditioned on at least the semantic representation and the embedding tokens, an acoustic representation of the audio signal; and processing at least the acoustic representation using a decoder neural network to generate the prediction of the audio signal.

Generating audio using auto-regressive generative neural networks

Methods, systems and apparatus, including computer programs encoded on computer storage media. According to one aspect, there is provided a method comprising: receiving a new input; processing the new input using an encoder neural network to generate a feature vector representing the new input; and generating a coded representation of the feature vector using a sequence of vector quantizers that are each associated with a respective codebook of code vectors, wherein the coded representation of the feature vector identifies a plurality of code vectors, including a respective code vector from the codebook of each vector quantizer, that define a quantized representation of the feature vector.

Generating coded data representations using neural networks and vector quantizers

The technology generally relates to spatial audio communication between devices. For example, a first device and a second device may be connected via a communication link. The first device may capture audio signals in an environment through two or more microphones. The first device may encode the captured audio with spatial configuration data. The first device may transmit the encoded audio via the communication link to the second device. The second device may decode the encoded audio into binaural or ambisonic audio to be output by one or more speakers of the second device. The binaural or ambisonic audio may be converted into spatial audio to be output. The second device may output the binaural or spatial audio to create an immersive listening experience.

Spatial audio recording from home assistant devices

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing an input audio waveform using a generator neural network to generate an output audio waveform. In one aspect, a method comprises: receiving an input audio waveform; processing the input audio waveform using an encoder neural network to generate a set of feature vectors representing the input audio waveform; and processing the set of feature vectors representing the input audio waveform using a decoder neural network to generate an output audio waveform that comprises a respective output audio sample for each of a plurality of output time steps.

Generating audio waveforms using encoder and decoder neural networks

Systems and methods for training a machine-learned model are provided. A method can include can include obtaining an unlabeled audio signal, sampling the unlabeled audio signal to select one or more sampled slices, inputting the one or more sampled slices into a machine-learned model, receiving, as an output of the machine-learned model, one or more determined characteristics associated with the audio signal, determining a loss function for the machine-learned model based at least in part on a difference between the one or more determined characteristics and one or more corresponding ground truth characteristics of the audio signal, and training the machine-learned model from end to end based at least in part on the loss function. The one or more determined characteristics can include one or more reconstructed portions of the audio signal temporally adjacent to the one or more sampled slices or an estimated distance between two sampled slices.

Self-supervised audio representation learning for mobile devices

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a prediction of an audio signal. One of the methods includes receiving a request to generate an audio signal; obtaining a semantic representation of the audio signal; generating, using one or more generative neural networks and conditioned on at least the semantic representation, an acoustic representation of the audio signal; and processing at least the acoustic representation using a decoder neural network to generate the prediction of the audio signal.

Methods, systems and apparatus, including computer programs encoded on computer storage media. One of the methods includes receiving an audio waveform that includes a respective audio sample for each of a plurality of time steps, processing the audio waveform using an encoder neural network to generate a plurality of feature vectors representing the audio waveform, generating a respective coded representation of each of the plurality of feature vectors using a plurality of vector quantizers that are each associated with a respective codebook of code vectors, wherein the respective coded representation of each feature vector identifies a plurality of code vectors, including a respective code vector from the codebook of each vector quantizer, that define a quantized representation of the feature vector, and generating a compressed representation of the audio waveform by compressing the respective coded representation of each of the plurality of feature vectors.

Compressing audio waveforms using neural networks and vector quantizers

Example embodiments relate to techniques for training artificial neural networks or oilier machine-learning encoders to accurately predict the pitch of input audio samples in a semitone or otherwise logarithmically-scaled pitch space. An example method may include generating, from a sample of audio data, two training samples by applying two different pitch shifts to the sample of audio training data. This can be done by converting the sample of audio data into the frequency domain and then shifting the transformed data. These known shifts are then compared to the predicted pitches generated by applying the two training samples to the encoder. The encoder is then updated based on the comparison, such that the relative pitch output by the encoder is improved with respect to accuracy. One or more audio samples, labeled with absolute pitch values, can then be used to calibrate the relative pitch values generated by the trained encoder.

Self-supervised pitch estimation

Growing community of inventors

Zurich, Switzerland

Marco Tagliasacchi