Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training neural networks through contrastive learning. In particular, the contrastive learning is modified to use a relative margin to adjust a training pair's contribution to optimization.

Abstract: Provided is an efficient approach to establish a foundational video-text model for tasks including open-vocabulary video classification, text-to-video retrieval, video captioning and video question-answering. Some example implementations include a model which can be referred to as VideoCoCa. Example implementations reuse a pretrained image-text contrastive captioner (CoCa) model and adapt it to video-text tasks with little or minimal extra training. While previous works adapt image-text models with various cross-frame fusion modules (for example, cross-frame attention layer or perceiver resampler) and finetune the modified architecture on video-text data, aspects of the present disclosure leverage findings that the generative attentional pooling and contrastive attentional pooling layers in the image-text CoCa design are instantly adaptable to “flattened frame embeddings”, yielding a strong zero-shot transfer baseline for many video-text tasks.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for training an audio-processing neural network that includes at least (1) a first encoder network having a first set of encoder network parameters and (2) a decoder network having a set of decoder network parameters. The system obtains a set of un-labeled audio data segments, and generates, from the set of un-labeled audio data segments, a set of encoder training examples. The system performs training of a second encoder neural network that includes at least the first encoder neural network on the set of generated encoder training examples. The system also obtains one or more labeled training examples, and performs training of the audio-processing neural network on the labeled training examples.

Abstract: Methods and systems for media item characterization based on multimodal embeddings are provided herein. A media item including a sequence of video frames is identified. A set of video embeddings representing visual features of the sequence of video frames is obtained. A set of audio embeddings representing audio features of the sequence of video frames is obtained. A set of audiovisual embeddings is generated based on the set of video embeddings and the set of audio embeddings. Each of the set of audiovisual embeddings represents a visual feature and an audio feature of a respective video frame of the sequence of video frames. One or more media characteristics associated with the media item are determined based on the set of audiovisual embeddings.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training neural networks through contrastive learning. In particular, the contrastive learning is modified to use a relative margin to adjust a training pair's contribution to optimization.

Abstract: Systems and methods for attribute recognition can include obtaining an image and a text string. The text string can be processed with a language model to generate a set of candidate attributes based on sequence based prediction. The image and the candidate attributes can be processed with an image-text model to determine a likelihood that the respective candidate attribute is depicted in the image. The likelihood determination can then be utilized to determine a predicted attribute for the object of interest.

Abstract: A method includes obtaining video datasets each including pairs of a training video and a ground-truth action classification of the training video. The method also includes generating an action recognition model that includes a shared encoder model and action classification heads. A number of the action classifications heads may be equal to a number of the video datasets, and each action classification head may be configured to, based on an output of the shared encoder model, classify training videos sampled from a corresponding video dataset. The method also includes determining, by the action recognition model and for each training video sampled from the video datasets, an inferred action classification. The method further includes determining a loss value based on the inferred action classifications and the ground-truth action classifications, and adjusting parameters of the action recognition model based on the loss value.

Abstract: A computer-implemented method includes receiving a sequence of acoustic frames as input to an automatic speech recognition (ASR) model. Here, the ASR model includes a causal encoder and a decoder. The method also includes generating, by the causal encoder, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method also includes generating, by the decoder, a first probability distribution over possible speech recognition hypotheses. Here, the causal encoder includes a stack of causal encoder layers each including a Recurrent Neural Network (RNN) Attention-Performer module that applies linear attention.

Abstract: Systems and methods are provided for vector-quantized image modeling using vision transformers and improved codebook handling. In particular, the present disclosure provides a Vector-quantized Image Modeling (VIM) approach that involves pre-training a machine learning model (e.g., Transformer model) to predict rasterized image tokens autoregressively. The discrete image tokens can be encoded from a learned Vision-Transformer-based VQGAN (example implementations of which can be referred to as ViT-VQGAN). The present disclosure proposes multiple improvements over vanilla VQGAN from architecture to codebook learning, yielding better efficiency and reconstruction fidelity. The improved ViT-VQGAN further improves vector-quantized image modeling tasks, including unconditional image generation, conditioned image generation (e.g., class-conditioned image generation), and unsupervised representation learning.

Abstract: An automated speech recognition (ASR) model includes a first encoder, a second encoder, and a decoder. The first encoder receives, as input, a sequence of acoustic frames, and generates, at each of a plurality of output steps, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The second encoder receives, as input, the first higher order feature representation generated by the first encoder at each of the plurality of output steps, and generates, at each of the plurality of output steps, a second higher order feature representation for a corresponding first higher order feature frame. The decoder receives, as input, the second higher order feature representation generated by the second encoder at each of the plurality of output steps, and generates, at each of the plurality of time steps, a first probability distribution over possible speech recognition hypotheses.

Abstract: Systems and methods can utilize a conformer model to process a data set for various data processing tasks, including, but not limited to, speech recognition, sound separation, protein synthesis determination, video or other image set analysis, and natural language processing. The conformer model can use feed-forward blocks, a self-attention block, and a convolution block to process data to learn global interactions and relative-offset-based local correlations of the input data.

Abstract: A computer-implemented method of training a streaming speech recognition model that includes receiving, as input to the streaming speech recognition model, a sequence of acoustic frames. The streaming speech recognition model is configured to learn an alignment probability between the sequence of acoustic frames and an output sequence of vocabulary tokens. The vocabulary tokens include a plurality of label tokens and a blank token. At each output step, the method includes determining a first probability of emitting one of the label tokens and determining a second probability of emitting the blank token. The method also includes generating the alignment probability at a sequence level based on the first probability and the second probability. The method also includes applying a tuning parameter to the alignment probability at the sequence level to maximize the first probability of emitting one of the label tokens.

Abstract: Systems and methods can utilize a conformer model to process a data set for various data processing tasks, including, but not limited to, speech recognition, sound separation, protein synthesis determination, video or other image set analysis, and natural language processing. The conformer model can use feed-forward blocks, a self-attention block, and a convolution block to process data to learn global interactions and relative-offset-based local correlations of the input data.

Abstract: Systems and methods are provided for vector-quantized image modeling using vision transformers and improved codebook handling. In particular, the present disclosure provides a Vector-quantized Image Modeling (VIM) approach that involves pretraining a machine learning model (e.g., Transformer model) to predict rasterized image tokens autoregressively. The discrete image tokens can be encoded from a learned Vision-Transformer-based VQGAN (example implementations of which can be referred to as ViT-VQGAN). The present disclosure proposes multiple improvements over vanilla VQGAN from architecture to codebook learning, yielding better efficiency and reconstruction fidelity. The improved ViT-VQGAN further improves vector-quantized image modeling tasks, including unconditional image generation, conditioned image generation (e.g., class-conditioned image generation), and unsupervised representation learning.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing multi-modal inputs using contrastive captioning neural networks.

Abstract: Example embodiments of the present disclosure relate to systems and methods for pretraining image-processing models on weakly-supervised image-text pairs. The pretraining can include receiving a training sequence for the machine-learned image-processing model. The training sequence can include text tokens and image tokens. A prefix sequence can contain the image tokens. A remainder sequence can include a remainder set of the text tokens. The pretraining can include determining, using the prefix sequence as an input to the machine-learned image-processing model, an objective based on recovery of the remainder sequence. The pretraining can include updating one or more learnable parameters of the machine-learned image-processing model based on the objective.

Abstract: Systems and methods of the present disclosure are directed to a computing system, including one or more processors and a machine-learned multi-mode speech recognition model configured to operate in a streaming recognition mode or a contextual recognition mode. The computing system can perform operations including obtaining speech data and a ground truth label and processing the speech data using the contextual recognition mode to obtain contextual prediction data. The operations can include evaluating a difference between the contextual prediction data and the ground truth label and processing the speech data using the streaming recognition mode to obtain streaming prediction data. The operations can include evaluating a difference between the streaming prediction data and the ground truth label and the contextual and streaming prediction data. The operations can include adjusting parameters of the speech recognition model.

Abstract: A computer-implemented method includes receiving a sequence of acoustic frames as input to an automatic speech recognition (ASR) model. Here, the ASR model includes a causal encoder and a decoder. The method also includes generating, by the causal encoder, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method also includes generating, by the decoder, a first probability distribution over possible speech recognition hypotheses. Here, the causal encoder includes a stack of causal encoder layers each including a Recurrent Neural Network (RNN) Attention-Performer module that applies linear attention.

Abstract: A method includes receiving a sequence of input audio frames corresponding to an utterance captured by a user device, the utterance including a plurality of words. For each input audio frame, the method includes predicting, using a word boundary detection model configured receive the sequence of input audio frames as input, whether the input audio frame is a word boundary. The method includes batching the input audio frames into a plurality of batches based on the input audio frames predicted as word boundaries, wherein each batch includes a corresponding plurality of batched input audio frames. For each of the plurality of batches, the method includes processing, using a speech recognition model, the corresponding plurality of batched input audio frames in parallel to generate a speech recognition result.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting a neural network to perform a particular machine learning task while satisfying a set of constraints.