Gm Global Technolgoy Operations, Inc.

Jason W Clark

Rathinavelu Chengalvarayan

Jeremy M Spaulding

Timothy Grost

John P Weiss

Dana Brian Fecher

Ryan J Wasson

Nathan D Ampunan

David M George

Edward J Abeska

Scott M Pennock

Jaycee Murlidar

A speech recognition method includes receiving input speech from a user, processing the input speech to obtain at least one parameter value, and determining an experience level of the user using the parameter value(s). The method can also include prompting the user based upon the determined experience level of the user to assist the user in delivering speech commands.

Automatically adapting user guidance in automated speech recognition

A method of operating a speech recognition system on a vehicle having a visual display and manually-operated input device that includes initiating a speech recognition system, controlling menu selections on a visual display using a manually-operated input device, receiving a notification from the manually-operated input device indicating that the user is manipulating the device in conjunction with the menu selections on the visual display, and adjusting operation of the speech recognition system based on input received by the manually-operated input device.

Speech recognition adjustment based on manual interaction

A speech recognition method includes the steps of receiving input speech containing vocabulary, processing the input speech with a grammar to obtain N-best hypotheses and associated parameter values, and determining whether a first-best hypothesis of the N-best hypotheses is confusable with any vocabulary within the grammar. The first-best hypothesis is accepted as recognized speech corresponding to the received input speech if the first-best hypothesis is not determined to be confusable with any vocabulary within the grammar. Where the first-best hypothesis is determined to be confusable, at least one parameter value of the first-best hypothesis can be compared to at least one threshold value, and accepting the second-best as the recognized speech, if its confidence score is within certain lower and upper threshold values and is not confusable with the first-best. The first-best hypothesis can be accepted as recognized speech corresponding to the received input speech, if the parameter value of the first-best hypothesis is greater than the threshold value.

Correcting substitution errors during automatic speech recognition by accepting a second best when first best is confusable

A voice dialing method includes the steps of receiving an utterance from a user, decoding the utterance to identify a recognition result for the utterance, and communicating to the user the recognition result. If an indication is received from the user that the communicated recognition result is incorrect, then it is added to a rejection reference. Then, when the user repeats the misunderstood utterance, the rejection reference can be used to eliminate the incorrect recognition result as a potential subsequent recognition result. The method can be used for single or multiple digits or digit strings.

Voice dialing using a rejection reference

A method of speech to DTMF generation involving ASR-enabled and DTMF-controlled communications systems. The ASR-enabled system is used to recognize speech received from the DTMF-controlled telecommunications system using sampling rate independent speech recognition. It then identifies a speech segment contained in the speech received from the DTMF-controlled system that corresponds with at least one keyword associated with user-defined data. Then, the ASR-enabled system transmits at least one DTMF signal to the DTMF-controlled system in response to the identified speech segment. This allows a user of an ASR-enabled system such as a vehicle telematics unit to at least partially automate access to the DTMF-controlled system using the telematics unit, so that voice mailbox numbers, passwords, and the like normally entered via a telephone keypad can be automatically sent to the DTMF-controlled system from the telematics unit without having to be manually input each time by the user.

Speech to DTMF generation

A method of managing communications for an in-vehicle telematics system includes substantially simultaneously receiving requests for communicating first and second audio signals via a vehicle audio system. The signals respectively correspond to interactive voice services (provided via a menu dialogue) from a first in-vehicle system and to a first audio messaging from a second in-vehicle system. An arbitration control selects one of the signals as a priority output and the other as a subordinate output. The priority output is provided over the audio system. A queue manager maintains the subordinate output in a queue for outputting over the audio system after priority output completion. If the first signal is the subordinate output, then the queue manager maintains a state of the menu dialogue, as of a time the priority output is selected, for continuation of the menu dialogue from the maintained state after priority output completion.

Growing community of inventors

Grosse Pointe Woods, MI, United States of America

Jason W Clark