Abstract: Voice Quality Enhancement is performed directly in a coded domain. At least one parameter of a first encoded signal is modified, which results in a corresponding at least one modified parameter. The at least one parameter of the first encoded signal is replaced with the at least one modified parameter, which results in a second encoded signal which, in a decoded state, approximates a target signal that is a function of at least the first encoded signal in at least a partially decoded state. Thus, the signal does not have to go through intermediate decoder/re-encoder(s), which can degrade overall speech quality. Computational resources required for a complete re-encoding are not needed. Overall delay of the system is minimized. The CD-VQE system can be used in any network in which signals are communicated in a coded domain, such as a Third Generation (3G) wireless network.

Abstract: Voice Quality Enhancement (VQE) is performed directly in a coded domain. A Coded Domain Voice Quality Enhancement (CD-VQE) system modifies at least one parameter of a first encoded signal, resulting in corresponding modified parameter(s). The CD-VQE system replaces the parameter(s) of the first encoded signal with the modified parameter(s), resulting in a second encoded signal. In a decoded state, the second encoded signal approximates a target signal that is a function of at least the first encoded signal in at least a partially decoded state. Thus, the first encoded signal does not have to go through intermediate decode/re-encode processes, which can degrade overall speech quality. The CD-VQE system may cascade functions. Computational resources required for a complete re-encoding are not needed. Overall delay of the system is minimized. The CD-VQE system can be used in networks in which signals are communicated in a coded domain, such as a Third Generation (3G) wireless network.

Abstract: Signal Quality Enhancement is performed directly in a coded domain. Coded Domain-Signal Quality Enhancement (CD-SQE) is applied to an encoded signal populated substantially with encoded signal bits to produce an enhanced encoded signal. The enhanced encoded signal is outputted. Thus, the signal does not have to go through intermediate decoder/re-encoder(s), which can degrade overall speech quality. Computational resources required for a complete re-encoding are not needed. Overall delay of the system is minimized. The CD-SQE system can be used in any network in which signals are communicated in a coded domain, such as a Third Generation (3G) wireless network.

Abstract: Adaptive Level Control (ALC) is performed directly in a coded domain. A Coded Domain Adaptive Level Control (CD-ALC) system modifies at least one parameter of a first encoded signal, resulting in corresponding modified parameter(s). The CD-ALC system replaces the parameter(s) of the first encoded signal with the modified parameter(s), resulting in a second encoded signal. In a decoded state, the second encoded signal approximates a target signal that is a function of the first encoded signal in at least a partially decoded state. Thus, the first encoded signal does not have to go through intermediate decode/re-encode processes, which can degrade overall speech quality. Computational resources required for a complete re-encoding are not needed. Overall delay of the system is minimized. The CD-ALC system can be used in any network in which signals are communicated in a coded domain, such as a Third Generation (3G) wireless network.

Abstract: Acoustic Echo Suppression (AES) or ES is performed directly in a coded domain. A Coded Domain Acoustic Echo Suppression (CD-AES) system modifies at least one parameter of a first encoded signal, resulting in corresponding modified parameter(s). The CD-AES system replaces the parameter(s) of the first encoded signal with the modified parameter(s), resulting in a second encoded signal which, in a decoded state, approximates a target signal that is a function of two signals, including the first encoded signal and a third encoded signal, in at least partially decoded states. Thus, the first encoded signal does not have to go through intermediate decode/re-encode processes, which can degrade overall speech quality. Computational resources required for a complete re-encoding are not needed. Overall delay of the system is minimized. The CD-AES system can be used in any network in which signals are communicated in a coded domain, such as a Third Generation (3G) wireless network.

Abstract: Noise Reduction (NR) is performed directly in a coded domain. A Coded Domain Noise Reduction (CD-NR) system modifies at least one parameter of a first encoded signal, resulting in corresponding modified parameter(s). The CD-NR system replaces the parameter(s) of the first encoded signal with the modified parameter(s), resulting in a second encoded signal which, in a decoded state, approximates a target signal that is a function of the first encoded signal in at least a partially decoded state. Thus, the first encoded signal does not have to go through intermediate decode/re-encode processes, which can degrade overall speech quality. Computational resources required for a complete re-encoding are not needed. Overall delay of the system is minimized. The CD-NR system can be used in any network in which signals are communicated in a coded domain, such as a Third Generation (3G) wireless network.

Abstract: A high reliability digit string recognizer/rejection system that processes spoken words through an HMM recognizer to determine a string of candidate digits, a filler model for each digit in the digit string, and other information. Next, a weighted sum is generated for each digit in the string and for a filler model for each digit in the string. A confidence score is generated for each digit by subtracting the filler weighted sum from the digit weighted sum. The confidence score for each digit is then compared to a threshold and, if the confidence score for any of the digits is less than the threshold, the entire digit string is rejected. If the confidence scores for all of the digits in the digit string are equal to or greater than the threshold, then the candidate digit string is accepted as a digit string.

Abstract: A two-pass classification system and method that post-processes HMM scores with additional confidence scores to derive a value that may be applied to a threshold on which a keyword verses non-keyword determination may be based. The first stage comprises Generalized Probabilistic Descent (GPD) analysis which uses feature vectors of the spoken words and the HMM segmentation information (developed by the HMM detector during processing) as inputs to develop a first set of confidence scores through a linear combination (a weighted sum) of the feature vectors of the speech. The second stage comprises a linear discrimination method that combines the HMM scores and the confidence scores from the GPD stage with a weighted sum to derive a second confidence score. The output of the second stage may then be compared to a predetermined threshold to determine whether the spoken word or words include a keyword.

Abstract: A method and apparatus for detecting dual-tone, multi-frequency (DTMF) digits and call progress tones by determining the amplitudes of preselected frequencies in a signal over a predetermined time period, and determining a candidate tone by selecting two of the preselected frequencies with the highest amplitudes and comparing the two selected frequencies to known DTMF and call progress tone frequencies. The amplitudes of the two selected frequencies are then tested against predefined thresholds corresponding to a candidate tone having the two selected frequencies. The candidate tone in the current time period is tested against candidate tones in previous time periods for consistency. If the candidate tone is a DTMF digit and passed all of the tests, then the DTMF digit is returned. If the candidate tone is a call progress tone, the pattern of the candidate tone over a plurality of predetermined time periods is recorded and tested against known patterns of the candidate tone.