Abstract: A speech recognition method includes the steps of receiving speech in a vehicle, extracting acoustic data from the received speech, and applying a vehicle-specific inverse impulse response function to the extracted acoustic data to produce normalized acoustic data. The speech recognition method may also include one or more of the following steps: pre-processing the normalized acoustic data to extract acoustic feature vectors; decoding the normalized acoustic feature vectors using as input at least one of a plurality of global acoustic models built according to a plurality of Lombard levels of a Lombard speech corpus covering a plurality of vehicles; calculating the Lombard level of vehicle noise; and/or selecting the at least one of the plurality of global acoustic models that corresponds to the calculated Lombard level for application during the decoding step.

Abstract: A speech recognition method includes receiving input speech from a user, processing the input speech using a first grammar to obtain parameter values of a first N-best list of vocabulary, comparing a parameter value of a top result of the first N-best list to a threshold value, and if the compared parameter value is below the threshold value, then additionally processing the input speech using a second grammar to obtain parameter values of a second N-best list of vocabulary. Other preferred steps include: determining the input speech to be in-vocabulary if any of the results of the first N-best list is also present within the second N-best list, but out-of-vocabulary if none of the results of the first N-best list is within the second N-best list; and providing audible feedback to the user if the input speech is determined to be out-of-vocabulary.

Abstract: A speech recognition method includes receiving a nametag utterance, decoding the nametag utterance to recognize constituent subwords of the nametag utterance, determining the number of subwords in the nametag utterance, and associating the nametag utterance with one or more of a plurality of different nametag clusters based on the number of subwords in the nametag utterance. According to preferred aspects of the method, a confusability check is performed on the nametag utterance within the cluster(s) associated with the nametag utterance, stored nametags are received from memory by decoding the nametag utterance within the cluster(s) associated with the nametag utterance, and the stored nametags are played back by cluster.

Abstract: A method for presenting a navigation route to a user of a vehicle includes generating a navigation route. An audio prompt is played through a predetermined component of a vehicle audio system, where the predetermined component spatially corresponds to a direction of an upcoming maneuver of the navigation route.

Abstract: A method for dynamic nametag scoring includes receiving at least one confusion table including at least one circumstantial condition wherein the confusion table is based on a plurality of phonetically balanced utterances, determining a plurality of templates for the nametag based on the received confusion tables, and determining a global nametag score for the nametag based on the determined templates. A computer usable medium with suitable computer program code is employed for dynamic nametag scoring.

Abstract: A method of customizing speech recognition in a mobile vehicle communication system is provided. A speech input is received at a telematics unit in communication with a call center, the speech input associated with a failure mode notification. The speech input is recorded at the telematics unit then forwarded to the call center via a wireless network based on the failure mode notification. At least one user-specific voice-recognition set is then received from the call center in response to the failure mode notification, wherein the user-specific voice-recognition set has been updated with the speech input. Systems and programs of customizing speech recognition in a mobile vehicle communication system are also provided.

Abstract: A speech recognition method comprising the steps of: storing multiple recognition models for a vocabulary set, each model distinguished from the other models in response to a Lombard characteristic, detecting at least one speaker utterance in a motor vehicle, selecting one of the multiple recognition models in response to a Lombard characteristic of the at least one speaker utterance, utilizing the selected recognition model to recognize the at least one speaker utterance; and providing a signal in response to the recognition.

Abstract: A method for managing user nametags for a vehicle communications system includes receiving a nametag transfer request at a call center from a source, determining a target vehicle based on the request, generating a nametag data file including a text data file, a phoneme set, and an audio data file for each nametag, and transmitting the nametag data file to the target vehicle.

Abstract: A method for managing user nametags for a vehicle communications system, the method including receiving a nametag transfer request at a call center from a source, determining a target vehicle associated with the source based on the request and modifying a source nametag data file based on an acoustic profile of the target vehicle, wherein the source nametag data file is one of an audio file and a text file.

Abstract: A method for improving recognition results of a speech recognizer uses supplementary information to confirm recognition results. A user inputs speech to a speech recognizer. The speech recognizer resides on a mobile device or on a server at a remote location. The speech recognizer determines a recognition result based on the input speech. A confidence measure is calculated for the recognition result. If the confidence measure is below a threshold, the user is prompted for supplementary data. The supplementary data is determined dynamically based on ambiguities between the input speech and the recognition result, wherein the supplementary data will distinguish the input speech over potential incorrect results. The supplementary data may be a subset of alphanumeric characters that comprise the input speech, or other data associated with a desired result, such as an area code or location. The user may provide the supplementary data verbally, or manually using a keypad, touchpad, touchscreen, or stylus pen.

Abstract: The central concept underlying the invention is to combine the human expertise supplied by an operator with speaker authentication technology installed on a machine. Accordingly, a speaker authentication system includes a speaker interface receiving a speech input from a speaker at a remote location. A speaker authentication module performs a comparison between the speech input and one or more speaker biometrics stored in memory. An operator interface communicates results of the comparison to a human operator authorized to determine identity of the speaker.

Abstract: An indexing system for tagging a media stream is provided. The indexing system includes a plurality of inputs for defining at least one tag. A tagging system assigns the tag to the media stream. A tag analysis system selectively distributes tags for review and editing by members of the collaborative group. A tag database stores the tag and the media stream. Retrieval architecture can search the database using the tags.

Abstract: System speakers are switched to function as sound input transducers to improve recognizer performance and to support recognizer features. A crossbar switch is selectively activated, either manually or under software control, to allow system loudspeakers to function as sound input transducers that supplement the recognition system microphone or microphone array. Using loudspeakers as “microphones” improves speech recognition in noisy environments, thus attaining better recognition performance with little added system cost. The loudspeakers, positioned in physically separate locations also provide spatial information that can be used to determine the location of the person speaking and thereby offer different functionality for different persons. Acoustic models are selected based on environmental and vehicle operating conditions and may be adapted dynamically using ambient information obtained using the loudspeakers as sound input transducers.

Abstract: System speakers are switched to function as sound input transducers to improve recognizer performance and to support recognizer features. A crossbar switch is selectively activated, either manually or under software control, to allow system loudspeakers to function as sound input transducers that supplement the recognition system microphone or microphone array. Using loudspeakers as “microphones” improves speech recognition in noisy environments, thus attaining better recognition performance with little added system cost. The loudspeakers, positioned in physically separate locations also provide spatial information that can be used to determine the location of the person speaking and thereby offer different functionality for different persons. Acoustic models are selected based on environmental and vehicle operating conditions and may be adapted dynamically using ambient information obtained using the loudspeakers as sound input transducers.

Abstract: A method for improving recognition results of a speech recognizer uses supplementary information to confirm recognition results. A user inputs speech to a speech recognizer. The speech recognizer resides on a mobile device or on a server at a remote location. The speech recognizer determines a recognition result based on the input speech. A confidence measure is calculated for the recognition result. If the confidence measure is below a threshold, the user is prompted for supplementary data. The supplementary data is determined dynamically based on ambiguities between the input speech and the recognition result, wherein the supplementary data will distinguish the input speech over potential incorrect results. The supplementary data may be a subset of alphanumeric characters that comprise the input speech, or other data associated with a desired result, such as an area code or location. The user may provide the supplementary data verbally, or manually using a keypad, touchpad, touchscreen, or stylus pen.

Abstract: An automatic speech recognition system for the condition that an incoming caller's speech is quiet and a resulting echo (of a loud playing prompt) can cause the residual (the portion of the echo remaining after even echo cancellation) to be of the magnitude of the incoming speech input. Such loud echoes can falsely trigger the speech recognition system and interfere with the recognition of valid input speech. An echo model has been proven to alleviate this fairly common problem and to be effective in eliminating such false triggering. Further, this automatic speech recognition system enhanced the recognition of valid speech was provided within an existing hidden Markov modeling framework.

Abstract: A method and apparatus for first training and then recognizing speech. The method and apparatus use subband cepstral features to improve the recognition string accuracy rates for speech inputs.

Abstract: A method and apparatus using a combined MLLR and MCE approach to estimating the time-varying polynomial Gaussian mean functions in the trended HMM has advantageous results. This integrated approach is referred to as the minimum classification error linear regression (MCELR), which has been developed and implemented in speaker adaptation experiments using a large body of utterances from different types of speakers. Experimental results show that the adaptation of linear regression on time-varying mean parameters is always better when fewer than three adaptation tokens are used.

Abstract: The proposed model aims at finding an optimal linear transformation on the Mel-warped DFT features according to the minimum classification error (MCE) criterion. This linear transformation, along with the (NSHMM) parameters, are automatically trained using the gradient descent method. An advantageous error rate reduction can be realized on a standard 39-class TIMIT phone classification task in comparison with the MCE-trained NSHMM using conventional preprocessing techniques.

Abstract: A class of features related to voicing parameters that indicate whether the vocal chords are vibrating. Features describing voicing characteristics of speech signals are integrated with an existing 38-dimensional feature vector consisting of first and second order time derivatives of the frame energy and of the cepstral coefficients with their first and second derivatives. Hidden Markov Model (HMM)-based connected digit recognition experiments comparing the traditional and extended feature sets show that voicing features and spectral information are complementary and that improved speech recognition performance is obtained by combining the two sources of information.