Gm Global Technolgoy Operations, Inc.

Kenneth R Booker

Gaurav Talwar

Xu Fang Zhao

Alaa M Khamis

Russell A Patenaude

Scott Thomas Droste

Jeffery John Milton

William L Villaire

Scott M Pennock

Mathew Anthony Clifford Keith Jones

A vehicle system includes a user device configured to produce acoustic sounds at varying frequencies. The vehicle system also includes a vehicle microphone for collecting acoustic data from the user device. Additionally, the vehicle system includes a vehicle processor for storing vehicle data including the acoustic data and a server communicatively coupled to the vehicle processor. In some examples, the server is configured to determine if the acoustic data match one or more predetermined frequencies of sound.

Vehicle system for detecting acoustic frequencies

The concepts include a user support system in the form of a microphone, a visual display arranged in a vehicle cabin, and a controller. The controller includes an instruction set that is executable to receive, via the microphone, a voice-based request from a user, and employ a virtual assistant to determine a user interaction in real time and to determine a specific intent for the voice-based request, including capturing metadata. A user interaction routine determines a user interaction parameter associated with the virtual assistant based upon the voice-based request from the user. A user sentiment analysis routine determines a user satisfaction parameter associated with the virtual assistant based upon the voice-based request from the user. The controller responds in real-time to the voice-based request based upon the user satisfaction parameter and the user interaction parameter that are associated with the virtual assistant.

System and method for a voice-activated user support system

An automatic rain response system includes microphones of a vehicle, windshield wipers, and a controller. The microphones generate acoustic signals in response to rain. The controller is configured to receive a local weather condition, extract acoustic features from the acoustic signals, form feature vectors in response to the acoustic features and the local weather condition, classify the feature vectors to determine a current class among multiple classes, activate the windshield the wipers at a high speed in response to the current class being a heavy rain on a windshield class, activate the windshield wipers at a medium speed in response to the current class being a freezing rain on the windshield class, activate the windshield wipers at a low speed in response to the current class being a light rain on the windshield class, and deactivate the windshield wipers in response to the current class being a no rain class.

Automatic rain response system

Methods and apparatus are provided for diagnosing a vehicle. In one embodiment, a method includes: initiating, by a processor, a recording of a noise by at least one microphone based on user selection data from a user of the vehicle; receiving, by the processor, audio signal data based on the recording; generating, by the processor, vector data based on the audio signal data; processing, by the processor, the vector data with at least one trained machine, by the processor, learning model to determine a classification of the noise; predicting, by the processor, an action to be taken based on the classification; and storing, by the processor, the audio signal data, the classification, and the action in a datastore.

Automated deep learning based on customer driven noise diagnostic assist

A method and associated system for recognizing speech using multiple speech recognition algorithms. The method includes receiving speech at a microphone installed in a vehicle, and determining results for the speech using a first algorithm, e.g., embedded locally at the vehicle. Speech results may also be received at the vehicle for the speech determined using a second algorithm, e.g., as determined by a remote facility. The results for both may include a determined speech topic and a determined speech slotted value, along with corresponding confidence levels for each. The method may further include using at least one of the determined first speech topic and the received second speech topic to determine the topic associated with the received speech, even when the first speech topic confidence level of the first speech topic, and the second speech topic confidence level of the second speech topic are both a low confidence level.

Speech recognition arbitration logic

A system and method of automated speech recognition using a dynamically-adjustable listening timeout. The method includes: receiving speech signals representing a first speech segment during a first speech listening period; during the first speech listening period, processing the received speech signals representing the first speech segment to determine whether the first speech segment includes one or more insignificant utterances; adjusting a listening timeout in response to the determination of whether the first speech segment includes one or more insignificant utterances; listening for subsequent received speech using the adjusted listening timeout; and performing automatic speech recognition on the received speech signals and/or the subsequently received speech signals.

Automated speech recognition using a dynamically adjustable listening timeout

A processor receives a broadcast in a vehicle, select audio data from the broadcast, processes the audio data selected from the broadcast, determines a phonetic pattern of the selected audio data based on the processing, selects additional instances of audio data from the broadcast that resemble the selected audio data, processes the additional instances of audio data from the broadcast, determine phonetic patterns of the additional instances of audio data, and selects a plurality of phonetic patterns from the phonetic pattern of the selected audio data and the phonetic patterns of the additional instances of audio data. A transmitter transmits the plurality of phonetic patterns to a server to determine an optimal pronunciation of the selected audio data based on a statistical analysis of the plurality of phonetic patterns and to add the optimal pronunciation of the selected audio data to a database used to recognize speech in the vehicle.

Growing community of inventors

Grosse Pointe Woods, MI, United States of America

Kenneth R Booker