Abstract: Disclosed herein are example box blade assemblies and foldable assemblies for use with the same. The foldable assemblies can have two or more segments which are pivotally connected to each other, such that the assemblies can be moved between an unfolded configuration and a folded configuration. In some cases, the foldable assemblies can include an actuator configured to extend and retract to move the assemblies between the unfolded configuration and the folded configuration. A locking mechanism may also be included to lock the foldable assemblies in the unfolded configuration, and in some cases, to lock the actuator into an extended position. The locking mechanism may also be engaged by the actuator. The actuator may be in communication with a controller that allows the user of a work vehicle to control the operation of the actuator and thus the foldable assembly.

Abstract: A reconfigurable grading blade attachment for a work machine includes an attachment frame, a pivot beam extending transversely to the frame length, a left stabilizer wheel assembly pivotally coupled to the left portion of the pivot beam, a right stabilizer wheel assembly pivotally coupled to a right portion of the pivot beam, a center mount, a left hydraulic actuator pivotally coupled to the left portion of the pivot beam, a right hydraulic actuator pivotally coupled to the right portion of the pivot beam, and a grading blade extending transversely to the length of the work machine frame. Retraction of the left hydraulic actuator rotates the left stabilizer wheel assembly upwards about the left wheel lift axis. Retraction of the right hydraulic actuator rotates the right stabilizer wheel assembly upwards about the right wheel lift axis.

Abstract: A drive module assembly includes a housing defining a housing interior for containing a lubricant. The housing interior is further defined as a first housing interior and a second housing interior. The drive module assembly also includes a first input shaft configured to receive rotational torque from a first power source, a first gear train rotatably coupled to the first input shaft, a first output shaft rotatably coupled to the first gear train, a second input shaft configured to receive rotational torque from a second power source, a second gear train disposed rotatably coupled to the second input shaft, and a second output shaft rotatably coupled to the second gear train. The first housing interior and the second housing interior are fluidly separate from one another.

Abstract: A method includes obtaining a plurality of sets of private training utterances. Each corresponding set of private training utterances is obtained from a different source and associated with a speech domain that is different than the speech domains associated with the other sets of private training utterances. The method also includes training a speech recognition model by obtaining a current version of the speech recognition model, selecting a batch of private training utterances from one of the plurality of sets of private training utterances, determining a differentially private gradient for updating the current version of the speech recognition model based on the selected batch of private training utterances, and updating the current version of the speech recognition model using the differentially private gradient. The method also includes adapting the trained speech recognition model to learn how to recognize speech in a target speech domain.

Abstract: A method includes receiving, as input to an initial block of a stack of self-attention blocks of a speech enhancement model, an input concatenating short-time Fourier transform (STFT) coefficients for a single channel noisy input signal and upscaled STFT coefficients of a bone conducted signal (BCS) recorded by an accelerometer. The method includes generating, using a final block of the stack of self-attention blocks, an un-masked output based on the input concatenating STFT coefficients for the single channel noisy input signal. The method includes generating, using a masking layer, a masked single channel noisy input signal based on the un-masked output. The method includes generating, using an inverse STFT layer, enhanced input speech features corresponding to a target utterance based on the STFT coefficients for the single channel noisy input signal and the masked single channel noisy input signal.

Abstract: A method includes receiving a sequence of encoder input frames as input to an end-to-end model. The method also includes generating a sequence of encoder output frames based on the sequence of encoder input frames using an encoder of the end-to-end model. The encoder includes a stack of multi-head attention blocks arranged to apply an encoder reduction ratio on the sequence of encoder input frames. A number of encoder output frames generated as output from the encoder is reduced from a number of the encoder input frames received as input to the encoder by a factor proportional to the encoder reduction ratio applied by the stack of multi-head attention blocks. The method also includes decoding the sequence of encoder output frames into a sequence of output tokens using a decoder of the end-to-end model.

Abstract: A computer-implemented method includes receiving a sequence of acoustic frames corresponding to an utterance and generating a reference speaker embedding for the utterance. The method also includes receiving a target speaker embedding for a target speaker and generating feature-wise linear modulation (FiLM) parameters including a scaling vector and a shifting vector based on the target speaker embedding. The method also includes generating an affine transformation output that scales and shifts the reference speaker embedding based on the FiLM parameters. The method also includes generating a classification output indicating whether the utterance was spoken by the target speaker based on the affine transformation output.

Abstract: A multichannel neural frontend speech enhancement model includes a first pre-processor block, a second pre-processor block, a stack of self-attention blocks, a first masking layer, a second masking layer, and a phrase extraction layer. The first pre-processor receives short-time Fourier transform (STFT) coefficients for a single channel cleaned input signal and generates a maximum value of an embedding dimension of the cleaned input signal. The second pre-processor receives STFT coefficients for a single channel noisy input signal and generates a maximum value of an embedding dimension of the noisy input signal. The stack of self-attention blocks receives a stacked input of the embedding dimensions of the cleaned input signal and the noisy input signal and generates an un-masked output. The phrase extraction layer receives the un-masked output, a masked cleaned input signal, and a masked noisy input signal, and generate enhanced input speech features.

Abstract: A method includes receiving a training data set including un-transcribed speech utterances that each include audio-only data not paired with any corresponding transcription, and obtaining a plurality of training canary transcriptions each including a predetermined number of words that are out-of-distribution from words of the un-transcribed speech utterances. For each training canary transcription, the method also includes generating, using TTS system, a corresponding synthetic training canary speech utterance that recites the predetermined number of words of the training canary transcription and pre-training an audio encoder on a combination of the un-transcribed speech utterances and the synthetic training canary speech utterances. The method also includes measuring an un-intended memorization of the pre-trained audio encoder based on encoder labels predicted by the pre-trained encoder for the synthetic training canary speech utterances.

Abstract: A method includes pre-training an audio encoder on a public training utterance set and from a corpus of text utterances, sampling a predetermined number of most frequent words that appear in the corpus of text utterances. The method also includes randomly generating a predetermined number of transcripts, and for each corresponding transcripts, processing, using a TTS system, the corresponding transcript to generate a corresponding synthetic speech utterance. The corresponding transcript and the corresponding synthetic speech utterance form a corresponding synthetic training sample. During a first fine-tuning stage, the method also includes fine-tuning an ASR model on the synthetic training samples.

Abstract: A method for training a generalized automatic speech recognition model for joint acoustic echo cancellation, speech enhancement, and voice separation includes receiving a plurality of training utterances paired with corresponding training contextual signals. The training contextual signals include a training contextual noise signal including noise prior to the corresponding training utterance, a training reference audio signal, and a training speaker vector including voice characteristics of a target speaker that spoke the corresponding training utterance. The operations also include training, using a contextual signal dropout strategy, a contextual frontend processing model on the training utterances to learn how to predict enhanced speech features. Here, the contextual signal dropout strategy uses a predetermined probability to drop out each of the training contextual signals during training of the contextual frontend processing model.

Abstract: A grading blade attachment for a work machine comprising an attachment frame including an upper attachment frame portion and a rear attachment frame portion wherein the upper attachment frame portion has a frame length extending forward from the rear attachment frame portion. The attachment further includes a coupler bracket, a pivot beam, a left wheel assembly, a right wheel assembly, a grading blade, and a knock down blade. The knock down blade assembly is movably coupled to the upper attachment frame portion between an operative position and an inoperative position. The knock down blade assembly including a knock down blade positioned fore of the wheel assemblies connected to the upper attachment frame portion when in the operative position.

Abstract: Implementations described herein are directed to techniques for eliminating and/or mitigating memorization by machine learning (ML) model(s). Processor(s) can obtain a plurality of training instances to be utilized in training a ML model, identify a plurality of compute cores (e.g., TPUs, GPUs, CPUs, FPGAs, ASICs, etc.), and generate a corresponding per-core gradient at each of the plurality of compute cores. Further, the processor(s) can update the ML model based on the corresponding per-core gradients. In generating the corresponding per-core gradient at a given compute core, the processor(s) can generate corresponding gradients based on a subset of the training instances, determine, based on the corresponding gradients, a corresponding mean gradient, and clip, based on a clipping bound, the corresponding mean gradient for the given compute core to generate the corresponding per-core gradient.

Abstract: A computer-implemented method includes receiving a sequence of acoustic frames corresponding to an utterance and generating a reference speaker embedding for the utterance. The method also includes receiving a target speaker embedding for a target speaker and generating feature-wise linear modulation (FiLM) parameters including a scaling vector and a shifting vector based on the target speaker embedding. The method also includes generating an affine transformation output that scales and shifts the reference speaker embedding based on the FiLM parameters. The method also includes generating a classification output indicating whether the utterance was spoken by the target speaker based on the affine transformation output.

Abstract: A method includes receiving a frequency-domain representation of an output audio signal output from a linear acoustic echo canceller (LAEC). The output audio signal includes target speech captured by an audio capture device of a user device and residual echo of reference audio output by an audio output device of the user device. The method also includes receiving a frequency-domain representation of the reference audio and determining, using a neural echo suppressor (NES), based on the frequency-domain representation of the output audio signal and the frequency-domain representation of the reference audio, a time-frequency mask. The method also includes processing, using the time-frequency mask, the frequency-domain representation of the output audio signal to attenuate the residual echo in an enhanced audio signal.

Abstract: A method includes receiving text-to-speech (TTS) data and outputting synthetic speech using an audio output device of a user device. The method also includes receiving an input audio data stream captured using an audio capture device of the user device and determining a first frame boundary in the input audio data stream. The input audio data stream includes target speech and an echo of the synthetic speech, while the first frame boundary represents a first alignment of the TTS data and the echo of the synthetic speech. Using a linear acoustic echo canceller, the method also includes determining a second frame boundary in the input audio data stream and processing the input audio data stream based on the second frame boundary to generate enhanced audio. The second frame boundary represents a second alignment of the TTS data and the echo of the synthetic speech.

Abstract: A reconfigurable grading blade attachment for a work machine includes an attachment frame, a pivot beam extending transversely to the frame length, a left stabilizer wheel assembly pivotally coupled to the left portion of the pivot beam, a right stabilizer wheel assembly pivotally coupled to a right portion of the pivot beam, a center mount, a left hydraulic actuator pivotally coupled to the left portion of the pivot beam, a right hydraulic actuator pivotally coupled to the right portion of the pivot beam, and a grading blade extending transversely to the length of the work machine frame. Retraction of the left hydraulic actuator rotates the left stabilizer wheel assembly upwards about the left wheel lift axis. Retraction of the right hydraulic actuator rotates the right stabilizer wheel assembly upwards about the right wheel lift axis.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an automated calling system are disclosed. In one aspect, a method includes the actions of receiving audio data of an utterance spoken by a user who is having a telephone conversation with a bot. The actions further include determining a context of the telephone conversation. The actions further include determining a user intent of a first previous portion of the telephone conversation spoken by the user and a bot intent of a second previous portion of the telephone conversation outputted by a speech synthesizer of the bot. The actions further include, based on the audio data of the utterance, the context of the telephone conversation, the user intent, and the bot intent, generating synthesized speech of a reply by the bot to the utterance. The actions further include, providing, for output, the synthesized speech.

Abstract: A box blade grading attachment of the present disclosure may comprise an attachment frame, a coupler bracket, a tilt connection, a pivot beam, left and right caster wheels, a grading box, and a tilting actuator. The attachment frame includes a rear attachment frame portion for coupling of the box blade grading attachment to a construction machine and an upper attachment frame portion having an upward facing reference surface. The tilt connection defines a tilt axis about which the attachment frame may tilt relative to the coupler bracket. The tilt axis may be substantially parallel to the upward facing reference surface. The pivot beam is pivotally connected to the upper attachment frame portion and includes left and right caster wheels pivotally connected to the pivot beam. The tilting actuator tilts the attachment frame and the grading box about the tilt axis relative to the coupler bracket.

Abstract: A method for automatic speech recognition using joint acoustic echo cancellation, speech enhancement, and voice separation includes receiving, at a contextual frontend processing model, input speech features corresponding to a target utterance. The method also includes receiving, at the contextual frontend processing model, at least one of a reference audio signal, a contextual noise signal including noise prior to the target utterance, or a speaker embedding including voice characteristics of a target speaker that spoke the target utterance. The method further includes processing, using the contextual frontend processing model, the input speech features and the at least one of the reference audio signal, the contextual noise signal, or the speaker embedding vector to generate enhanced speech features.