Abstract: 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.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an audio signal from input text. In one aspect, a method comprises receiving a request to convert input text into an audio signal, wherein the input text comprises multiple tokenized text inputs, generating, using a first generative neural network, a semantic representation of the tokenized text inputs comprising semantic tokens representing semantic content of the tokenized text inputs, each semantic token being selected from a vocabulary of semantic tokens, generating, using a second generative neural network and conditioned on at least the semantic representation, an acoustic representation of the semantic representation comprising one or more respective acoustic tokens representing acoustic properties of the audio signal, and processing the acoustic representation using a decoder neural network to generate the audio signal.

Abstract: 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.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing speech separation. One of the methods includes obtaining a recording comprising speech from a plurality of speakers; processing the recording using a speaker neural network having speaker parameter values and configured to process the recording in accordance with the speaker parameter values to generate a plurality of per-recording speaker representations, each speaker representation representing features of a respective identified speaker in the recording; and processing the per-recording speaker representations and the recording using a separation neural network having separation parameter values and configured to process the recording and the speaker representations in accordance with the separation parameter values to generate, for each speaker representation, a respective predicted isolated audio signal that corresponds to speech of one of the speakers in the recording.

Abstract: A system and method are disclosed. Audio input comprising the mixed audio signals is received by one or more client devices. The audio input is converted into a plurality of discrete tokens. A plurality of sound sources, each corresponding to a subset of discrete tokens of a plurality of subsets of discrete tokens, is determined using a trained machine learning model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network and a decoder neural network. In one aspect, a method includes obtaining a first initial audio waveform and a first noisy audio waveform, obtaining a second initial audio waveform and a second noisy audio waveform, processing the first noisy audio waveform and the second noisy audio waveform using an encoder neural network, generating a blended embedding by concatenating: (i) clean feature dimensions from an embedding of the first noisy audio waveform, and (ii) noise feature dimensions from an embedding of the second noisy audio waveform, processing the blended embedding using a decoder neural network to generate a reconstructed audio waveform, determining gradients of an objective function; and updating parameter values of the encoder neural network and the decoder neural network using the gradients.

Abstract: 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.

Abstract: 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.

Abstract: A method of training a machine learning model, includes receiving training data for the machine learning model, wherein the training data comprises a plurality of batches. The method also includes applying a downsampling layer of the machine learning model to the plurality of batches of the training data to determine a stride comprising a learnable parameter for the downsampling layer. Applying the downsampling layer of the machine learning model to a batch of the training data includes projecting an input in a spatial domain to a Fourier domain, constructing a mask in the Fourier domain based on a current value of the stride and dimensions of the input, applying the mask as a low-pass filter to the projected input to produce a tensor in the Fourier domain, cropping the tensor based on the mask, and transforming the cropped tensor to the spatial domain.

Abstract: A method including identifying an audio capture device and a target direction associated with the audio capture device, detecting first audio associated with the target direction, enhancing the first audio using a machine learning model configured to detect audio associated with the target direction, optionally, detecting second audio associated with a direction different from the target direction, and optionally, diminishing the second audio using the machine learning model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing tasks. One of the methods includes obtaining a sequence of input tokens, where each token is selected from a vocabulary of tokens that includes text tokens and audio tokens, and wherein the sequence of input tokens includes tokens that describe a task to be performed and data for performing the task; generating a sequence of embeddings by embedding each token in the sequence of input tokens in an embedding space; and processing the sequence of embeddings using a language model neural network to generate a sequence of output tokens for the task, where each token is selected from the vocabulary.

Abstract: Training data comprising a plurality of training pairs is obtained. Each training pair comprises instrumental audio data and vocal audio data separated from audio data of a musical work of a respective plurality of musical works. For one or more training pairs of the plurality of training pairs, the vocal audio data is processed with machine-learned model(s) of a machine-learned generative audio model grouping to obtain a vocal intermediate representation for the vocal audio data. The instrumental audio data is processed with a pre-trained encoding model to obtain an instrumental intermediate representation for the instrumental audio data. A loss function is evaluated that evaluates a difference between the vocal intermediate representation and the instrumental intermediate representation. Values of parameters of a machine-learned model of the machine-learned generative audio model grouping are modified based on the loss function.

Abstract: 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.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for jointly learning the architecture of a neural network during the training of the neural network. In particular, the architecture of the neural network is learned using differentiable parametric masks.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A method includes receiving an input audio signal corresponding to utterances spoken by multiple speakers. The method also includes encoding the input audio signal into a sequence of T temporal embeddings. During each of a plurality of iterations each corresponding to a respective speaker of the multiple speakers, the method includes selecting a respective speaker embedding for the respective speaker by determining a probability that the corresponding temporal embedding includes a presence of voice activity by a single new speaker for which a speaker embedding was not previously selected during a previous iteration and selecting the respective speaker embedding for the respective speaker as the temporal embedding. The method also includes, at each time step, predicting a respective voice activity indicator for each respective speaker of the multiple speakers based on the respective speaker embeddings selected during the plurality of iterations and the temporal embedding.

Abstract: 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.