Abstract: Method and apparatus are disclosed for responding to HVAC-induced vehicle microphone buffeting. An example disclosed vehicle includes a microphone, a speaker, and a buffeting detector. The example microphone is electrically coupled to an input of a voice-activated system. The example speaker is located on a front driver side of the vehicle. The example buffeting detector, when a button is activated, determines a buffeting factor of a signal captured by the microphone. Additionally, the example buffeting detector, in response to the buffeting factor satisfying a threshold, activates a relay to electrically couple the speaker to the input of the voice-activated system.

Abstract: Method and apparatus are disclosed for dialect and language recognition for speech detection in vehicles. An example vehicle includes a microphone, a communication module, memory storing acoustic models for speech recognition, and a controller. The controller is to collect an audio signal that includes a voice command and identify a dialect of the voice command by applying the audio signal to a deep neural network. The controller also is to download, upon determining the dialect does not correspond with any of the acoustic models, a selected acoustic model for the dialect from a remote server via the communication module.

Abstract: Method and apparatus are disclosed for accelerometer-based external sound monitoring for position aware autonomous parking. An example vehicle includes accelerometers mounted on windows of the vehicle, a computing platform communicatively coupled to the accelerometers, and an autonomy unit. The computing platform receives, via the accelerometers, signals indicative of a stop command associated with a voice. Additionally, the computing platform validates the stop command when the voice either is authorized or originates from within an emergency zone. The autonomy unit prevents autonomous motion of the vehicle in response to receiving the validated stop command.

Abstract: An automatic speech recognition system for a vehicle includes a controller configured to select an acoustic model from a library of acoustic models based on ambient noise in a cabin of the vehicle and operating parameters of the vehicle. The controller is further configured to apply the selected acoustic model to noisy speech to improve recognition of the speech.

Abstract: Method and apparatus are disclosed for monitoring of vehicle window vibrations for voice-command recognition. An example vehicle includes a window, an outer layer, a vibration sensor coupled to the window to detect audio vibrations, an audio actuator coupled to the outer layer to vibrate the outer layer, and a controller. The controller is to detect a voice command from a user via the vibration sensor, identify an audio response based upon the voice command, and emit the audio response to the user via the audio actuator.

Abstract: Method and apparatus are disclosed for accelerometer-based external sound monitoring for voice controlled autonomous parking. An example vehicle includes a body control module, an infotainment head unit, and an autonomy unit. The example body control module communicatively couples to a mobile device. The example infotainment head unit communicatively couples to an accelerometer mounted on a window of the vehicle. The example autonomy unit autonomously parks the vehicle in response to a first key word detected by the accelerometer when (i) a button is activated on the infotainment head unit and (ii) a message from the mobile device is being periodically received.

Abstract: Method and apparatus are disclosed for accelerometer-based external sound monitoring during low speed maneuvers. An example vehicle includes accelerometers affixed to windows of the vehicle, speakers located inside the vehicle, and an infotainment head unit. Each of the speakers is uniquely associated with one of the accelerometers. The infotainment head unit, when a speed of the vehicle satisfies a threshold, selects a zone corresponding to a direction of travel of the vehicle. Additionally, the infotainment head unit plays signals captured by the accelerometers associated with the selected zone on the corresponding speakers.

Abstract: Method and apparatus are disclosed for determining and accounting for distortions to an audio signal due to the geometric properties of the interior cabin of a vehicle. An example vehicle includes a microphone, a seat having a plurality of seat positions, and a processor. The processor is configured to determine a first seat position corresponding to a point in time at which an audio signal is received, determine a cabin impulse response corresponding to the first seat position, and determine a filtered audio signal based on the cabin impulse response and the audio signal.

Abstract: Voice control is extended outside of an automotive vehicle by an access system associated with a door and window. An accelerometer is mounted on the window to generate a vibration signal. A passive entry system generates an unlock standby signal when an authorized user carrying a wireless fob is detected proximate the door. A voice recognizer in the vehicle is activated by the standby signal to scan the vibration signal for a spoken command for opening the door. A door actuator is activated by the voice recognizer when the command is detected.

Abstract: Method and apparatus are disclosed for responding to HVAC-induced vehicle microphone buffeting. An example disclosed vehicle includes a microphone, a speaker, and a buffeting detector. The example microphone is electrically coupled to an input of a voice-activated system. The example speaker is located on a front driver side of the vehicle. The example buffeting detector, when a button is activated, determines a buffeting factor of a signal captured by the microphone. Additionally, the example buffeting detector, in response to the buffeting factor satisfying a threshold, activates a relay to electrically couple the speaker to the input of the voice-activated system.

Abstract: A processor of a vehicle speech recognition system recognizes speech via domain-specific language and acoustic models. The processor further, in response to the acoustic model having a confidence score for recognized speech falling within a predetermined range defined relative to a confidence score for the domain-specific language model, recognizes speech via the acoustic model only.

Abstract: An automatic speech recognition system for a vehicle includes a controller configured to select an acoustic model from a library of acoustic models based on ambient noise in a cabin of the vehicle and operating parameters of the vehicle. The controller is further configured to apply the selected acoustic model to noisy speech to improve recognition of the speech.

Abstract: A controller may be programmed to create a speech utterance set for speech recognition training by, in response to receiving data representing a neutral utterance and parameter values defining signal noise, generating data representing a Lombard effect version of the neutral utterance using a transfer function associated with the parameter values and defining distortion between neutral and Lombard effect versions of a same utterance due to the signal noise.