Abstract: The present disclosure provides materials and methods related to image processing. In particular, the present disclosure provides methods for enhancing target signal detection using imaging processing analysis that identifies and removes non-specific background signals. The image processing methods of the present disclosure are useful for enhancing target signals in a variety of assays that involve fluorescent detection (e.g., fluorescent in situ hybridization, immunofluorescence).

Abstract: A frequency hopping communication method for short-distance wireless communication between a primary device and a secondary device comprises switching by the primary device from the second frequency hopping sequence to the first frequency hopping sequence at a time point of frequency hopping switching, wherein M reserved channels are between a first frequency hopping sequence and a second frequency hopping sequence; and performing frequency hopping communication with the secondary device based on the first frequency hopping sequence.

Abstract: The invention relates to methods of multiplex detection of a plurality of target nucleic acids by contacting a sample comprising a cell with target probe sets that specifically hybridize to target nucleic acids, with pre-amplifiers or pre-pre-amplifiers specific for each target probe set, with amplifiers specific for the pre-amplifiers, and with label probes specific for the amplifiers, resulting in specific labeling of multiple target nucleic acids. The invention also relates to samples, slides and kits relating to detection of multiple target nucleic acids.

Abstract: A method of training an accent recognition model includes receiving a corpus of training utterances spoken across various accents, each training utterance in the corpus including training audio features characterizing the training utterance, and executing a training process to train the accent recognition model on the corpus of training utterances to teach the accent recognition model to learn how to predict accent representations from the training audio features. The accent recognition model includes one or more strided convolution layers, a stack of multi-headed attention layers, and a pooling layer configured to generate a corresponding accent representation.

Abstract: A method (500) includes receiving an input audio signal (122) that corresponds to utterances (120) spoken by multiple speakers. The method also includes processing the input audio to generate a transcription (200) of the utterances and a sequence of speaker turn tokens (224) each indicating a location of a respective speaker turn. The method also includes segmenting the input audio signal into a plurality of speaker segments (225) based on the sequence of speaker tokens. The method also includes extracting a speaker-discriminative embedding from each speaker segment and performing spectral clustering on the speaker-discriminative embeddings to cluster the plurality of speaker segments into k classes. The method also includes assigning a respective speaker label (250) to each speaker segment clustered into the respective class that is different than the respective speaker label assigned to the speaker segments clustered into each other class of the k classes.

Abstract: Embodiments of the present disclosure include compositions and methods for performing in situ hybridization reactions. In particular, the present disclosure provides RNA blocking molecules that enhance detection of a target RNA molecule (e.g., an mRNA molecule, a microRNA (miRNA) molecule, a small non-coding RNA (sncRNA) molecule, a PIWI-interacting RNA (piRNA) molecule, a small interfering RNA (siRNA) molecule, and/or an anti-sense oligo (ASO) molecule) by reducing binding of a target probe to a non-target RNA molecule in a sample.

Abstract: A method includes receiving an input audio signal that corresponds to utterances spoken by multiple speakers. The method also includes processing the input audio to generate a transcription of the utterances and a sequence of speaker turn tokens each indicating a location of a respective speaker turn. The method also includes segmenting the input audio signal into a plurality of speaker segments based on the sequence of speaker tokens. The method also includes extracting a speaker-discriminative embedding from each speaker segment and performing spectral clustering on the speaker-discriminative embeddings to cluster the plurality of speaker segments into k classes. The method also includes assigning a respective speaker label to each speaker segment clustered into the respective class that is different than the respective speaker label assigned to the speaker segments clustered into each other class of the k classes.

Abstract: The invention relates to methods of multiplex detection of a plurality of target nucleic acids by contacting a sample comprising a cell with target probe sets that specifically hybridize to target nucleic acids, with pre-amplifiers or pre-pre-amplifiers specific for each target probe set, with amplifiers specific for the pre-amplifiers, and with label probes specific for the amplifiers, resulting in specific labeling of multiple target nucleic acids. The invention also relates to samples, slides and kits relating to detection of multiple target nucleic acids.

Abstract: Some implementations relate to receiving input data; generating, using a low-rank representation of a machine-learned generative model, a generative output from the input data; determining, based on a machine-learned reward model, a corresponding reward from the generative output, and updating, based on the corresponding reward, one or more parameters of the low-rank representation of the machine-learned model. Further, some additional or alternative implementations relate to receiving input data associated with a client device; generating, using a general purpose agent, responsive content to the input data, wherein the general purpose agent is configured based on a machine-learned generative model and a low-rank representation of the machine-learned generative model; and causing the client device to render the responsive content.

Abstract: A method includes obtaining a multi-utterance training sample that includes audio data characterizing utterances spoken by two or more different speakers and obtaining ground-truth speaker change intervals indicating time intervals in the audio data where speaker changes among the two or more different speakers occur. The method also includes processing the audio data to generate a sequence of predicted speaker change tokens using a sequence transduction model. For each corresponding predicted speaker change token, the method includes labeling the corresponding predicted speaker change token as correct when the predicted speaker change token overlaps with one of the ground-truth speaker change intervals. The method also includes determining a precision metric of the sequence transduction model based on a number of the predicted speaker change tokens labeled as correct and a total number of the predicted speaker change tokens in the sequence of predicted speaker change tokens.

Abstract: A method (500) includes receiving, from an application (50) executing on a client device (110), at a speech service interface (200), configuration parameters (211) for integrating a speech service (250) into the application. The configuration parameters include a language pack directory (225) that maps a primary language code (235) to an on-device path of a primary language pack (110) of the speech service for use in recognizing speech in a primary language and each of one or more codeswitch language codes to an on-device path. The method also includes receiving audio data (102) characterizing an utterance (106) and processing, using a language ID predictor model (230), the audio data to determine that the audio data is associated with the primary language code. The method also includes processing, using the primary language pack, the audio data to determine a transcription (120) that includes one or more words in the primary language.

Abstract: A method includes receiving an input audio signal that corresponds to utterances spoken by multiple speakers. The method also includes processing the input audio to generate a transcription of the utterances and a sequence of speaker turn tokens each indicating a location of a respective speaker turn. The method also includes segmenting the input audio signal into a plurality of speaker segments based on the sequence of speaker tokens. The method also includes extracting a speaker-discriminative embedding from each speaker segment and performing spectral clustering on the speaker-discriminative embeddings to cluster the plurality of speaker segments into k classes. The method also includes assigning a respective speaker label to each speaker segment clustered into the respective class that is different than the respective speaker label assigned to the speaker segments clustered into each other class of the k classes.

Abstract: Methods of locating a target object in a ranging device and the ranging devices thereof are provided. First, a signal processor is used to process a first signal of a first signal module corresponding to a first target object, where the first signal at least includes location information. Then, a first target distance corresponding to the first target object is determined based on a device location of the ranging device and the location information in the first signal. After that, a laser ranging unit is used to perform a ranging operation on the first target object to obtain a first laser ranging result, and a display unit is used to display a first icon corresponding to the first target object according to the first target distance or the first laser ranging result.

Abstract: A wireless charging rangefinder includes at least one rangefinder body and a magnetic unit. The rangefinder body includes a distance measuring unit, a first control unit, a first power source, a first coil, an objective lens unit, and an eyepiece unit, wherein the distance measuring unit, the first power source and the first coil are electrically connected to the first control unit, and an optical axis is configured to pass through the objective lens unit and the eyepiece unit. The magnetic unit is placed with the first coil corresponding to a second coil of a charging device so that the charging device can charge the rangefinder body.

Abstract: A method includes receiving a plurality of unlabeled audio samples corresponding to spoken utterances not paired with corresponding transcriptions. At a target branch of a contrastive Siamese network, the method also includes generating a sequence of encoder outputs for the plurality of unlabeled audio samples and modifying time characteristics of the encoder outputs to generate a sequence of target branch outputs. At an augmentation branch of a contrastive Siamese network, the method also includes performing augmentation on the unlabeled audio samples, generating a sequence of augmented encoder outputs for the augmented unlabeled audio samples, and generating predictions of the sequence of target branch outputs generated at the target branch. The method also includes determining an unsupervised loss term based on target branch outputs and predictions of the sequence of target branch outputs. The method also includes updating parameters of the audio encoder based on the unsupervised loss term.

Abstract: A method includes receiving a sequence of acoustic frames extracted from unlabeled audio samples that correspond to spoken utterances not paired with any corresponding transcriptions. The method also includes generating, using a supervised audio encoder, a target higher order feature representation for a corresponding acoustic frame. The method also includes augmenting the sequence of acoustic frames and generating, as output form an unsupervised audio encoder, a predicted higher order feature representation for a corresponding augmented acoustic frame in the sequence of augmented acoustic frames. The method also includes determining an unsupervised loss term based on the target higher order feature representation and the predicted higher order feature representation and updating parameters of the speech recognition model based on the unsupervised loss term.

Abstract: A method includes obtaining labeled training data including a plurality of spoken terms spoken during a conversation. For each respective spoken term, the method includes generating a corresponding sequence of intermediate audio encodings from a corresponding sequence of acoustic frames, generating a corresponding sequence of final audio encodings from the corresponding sequence of intermediate audio encodings, generating a corresponding speech recognition result, and generating a respective speaker token representing a predicted identity of a speaker for each corresponding speech recognition result. The method also includes training the joint speech recognition and speaker diarization model jointly based on a first loss derived from the generated speech recognition results and the corresponding transcriptions and a second loss derived from the generated speaker tokens and the corresponding speaker labels.

Abstract: A method for training a speech recognition model with a loss function includes receiving an audio signal including a first segment corresponding to audio spoken by a first speaker, a second segment corresponding to audio spoken by a second speaker, and an overlapping region where the first segment overlaps the second segment. The overlapping region includes a known start time and a known end time. The method also includes generating a respective masked audio embedding for each of the first and second speakers. The method also includes applying a masking loss after the known end time to the respective masked audio embedding for the first speaker when the first speaker was speaking prior to the known start time, or applying the masking loss prior to the known start time when the first speaker was speaking after the known end time.

Abstract: A transformer-transducer model for unifying streaming and non-streaming speech recognition includes an audio encoder, a label encoder, and a joint network. The audio encoder receives a sequence of acoustic frames, and generates, at each of a plurality of time steps, a higher order feature representation for a corresponding acoustic frame. The label encoder receives a sequence of non-blank symbols output by a final softmax layer, and generates, at each of the plurality of time steps, a dense representation. The joint network receives the higher order feature representation and the dense representation at each of the plurality of time steps, and generates a probability distribution over possible speech recognition hypothesis. The audio encoder of the model further includes a neural network having an initial stack of transformer layers trained with zero look ahead audio context, and a final stack of transformer layers trained with a variable look ahead audio context.

Abstract: A streaming speech recognition model includes an audio encoder configured to receive a sequence of acoustic frames and generate a higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The streaming speech recognition model also includes a label encoder configured to receive a sequence of non-blank symbols output by a final softmax layer and generate a dense representation. The streaming speech recognition model also includes a joint network configured to receive the higher order feature representation generated by the audio encoder and the dense representation generated by the label encoder and generate a probability distribution over possible speech recognition hypotheses. Here, the streaming speech recognition model is trained using self-alignment to reduce prediction delay by encouraging an alignment path that is one frame left from a reference forced-alignment frame.