Lucent Technologies Inc.

Tellabs Operations, Inc.

At+t Corp.

At&t Bell Laboratories

Rafid Antoon Sukkar

Anand Rangaswamy Setlur

Yajun Wang

Julia Y Larikova

Richard Y Younce

Richard C Younce

Chin-Hui Lee

Raymond W Bennett

Peng Zhang

Joseph L LoCicero

Malan Bhatki Gandhi

Joseph G Klinger

Carl Dennis Mitchell

Carol Lynn Curt

Brian C Prorok

John Joseph Wisowaty

Grzegorz Szeszko

Method and apparatus of an optical routing system ('ORS') capable of automatically discovering intra-nodal fiber connections using a test channel transceiver ('TCT') are disclosed. ORS, in one embodiment, includes a set of reconfigurable optical add-drop multiplexer (&#x201c;ROADM&#x201d;) modules, intra-nodal fiber connections, add-drop modules, and a test module. The ROADM modules are able to transmit or receive optical signals via optical fibers. The intra-nodal fiber connections are configured to provide optical connections. The add-drop modules are able to selectively make connections between input ports and output ports. The test module containing TCT is configured to identify at least a portion of intra-nodal connections of the ROADM via a test signal operating with a unique optical frequency.

Methods and apparatus for providing configuration discovery using intra-nodal test channel

Adaptive Gain Control (AGC) is performed directly in a coded domain. A Coded Domain Adaptive Gain Control (CD-AGC) 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 two signals, including the first encoded signal and a third encoded signal, in at least a 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-AGC system can be used in any network in which signals are communicated in a coded domain, such as a Third Generation (3G) wireless network.

Method and apparatus for modifying an encoded signal for voice quality enhancement

A method and corresponding apparatus for coded-domain acoustic echo control is presented. An echo control problem is considered as that of perceptually matching an echo signal to a reference signal. A perceptual similarity function that is based on the coded spectral parameters produced by the speech codec is defined. Since codecs introduce a significant degree of non-linearity into the echo signal, the similarity function is designed to be robust against such effects. The similarity function is incorporated into a coded-domain echo control system that also includes spectrally-matched noise injection for replacing echo frames with comfort noise. Using actual echoes recorded over a commercial mobile network, it is shown herein that the similarity function is robust against both codec non-linearities and additive noise. Experimental results further show that the echo-control is effective at suppressing echoes compared to a Normalized Least Mean Squared (NLMS)-based echo cancellation system.

Method and apparatus for controlling echo in the coded domain

Speech recognition technology has attained maturity such that the most likely speech recognition result has been reached and is available before an energy based termination of speech has been made. The present invention innovatively uses the rapidly available speech recognition results to provide intelligent barge-in for voice-response systems, to count words to output sub-sequences to provide paralleling and/or pipelining of tasks related to the entire word sequence, and to count words to provide rapid, speech recognition based termination of speech processing and outputting of the recognized word sequence.

Method and apparatus for word counting in continuous speech recognition useful for reliable barge-in and early end of speech detection

Robust, multi-faceted sub-word method for rapidly and reliably detecting a barge-in condition of a speaker talking while an automated audio prompt is being played. This sub-word method allows for rapid stopping of the prompt to improve automatic speech recognition and reduce speaker confusion and/or frustration. An automatic speech recognition system (ASR) that practices such a method is also presented.

Method and apparatus for recognition-based barge-in detection in the context of subword-based automatic speech recognition

The apparatus, method and system of the present invention provide for cross-speaker speech recognition, and are particularly suited for telecommunication applications such as automatic name (voice) dialing, message management, call return management, and incoming call screening. The method of the present invention includes receiving incoming speech, such as an incoming caller name, and generating a phonetic transcription of the incoming speech with a speaker-independent, hidden Markov model having an unconstrained grammar in which any phoneme may follow any other phoneme, followed by determining a transcription parameter as a likelihood of fit of the incoming speech to the speaker-independent model. The method further selects a first phoneme pattern, from a plurality of phoneme patterns, as having a highest likelihood of fit to the incoming speech, utilizing a speaker-independent, hidden Markov model having a grammar constrained by these phoneme patterns, followed by determining a recognition parameter as a likelihood of fit of the incoming speech to the selected, first phoneme pattern. The method then determines whether the input speech matches or collides with the first phoneme pattern based upon a correspondence of the transcription parameter with the recognition parameter in accordance with a predetermined criterion. In the preferred embodiment, this matching or collision determination is made as a function of a confidence ratio, the ratio of the transcription parameter to the recognition parameter, being within or less than a predetermined threshold value.

Apparatus, method and system for cross-speaker speech recognition for telecommunication applications

An automated speech recognition system comprises a preprocessor, a speech recognizer, and a task-independent utterance verifier. The task independent utterance verifier employs a first subword acoustic Hidden Markov Model for determining a first likelihood that a speech segment contains a sound corresponding to a speech recognition hypothesis, and a second anti-subword acoustic Hidden Markov Model for determining a second likelihood that a speech segment contains a sound other than one corresponding to the speech recognition hypothesis. In operation, the utterance verifier employs the subword and anti-subword models to produce for each recognized subword in the input speech the first and second likelihoods. The utterance verifier determines a subword verification score as the log of the ratio of the first and second likelihoods. In order to verify larger speech units, the utterance verifier combines the subword verification scores to produce a word/phrase/sentence verification score, and compares that score to a predetermined threshold. The first and second verification-specific HMMs are discriminatively trained using a subword-based minimum verification error training technique.

Task-independent utterance verification with subword-based minimum verification error training

Method and apparatus for word counting in continuous speech recognition

A speech recognition method and apparatus which has a first stage to provide keyword hypotheses and a second stage to provide testing of those hypotheses by utterance verification. The utterance verification used has three separate models for each word: one keyword verification model, one misrecognition verification model, and one non-keyword verification model. Further, all three are developed independently of the recognizer keyword models. Because of this independence, the three verification models can be iteratively trained using existing speech data bases to jointly provide a minimum amount of verification errors.

Utterance verification using word based minimum verification error

A new speaker verification method, termed Mixture Decomposition Discrimination (MDD), and a new apparatus for using MDD are presented. MDD takes mixture component score information from a speaker independent recognizer and transmits this information while it is still decomposed as a mixture of component scores that indicate the response of the states of a Hidden Markov Model (HMM) before this information is combined into a single speaker independent recognizer parameter. MDD can be very effective in improving the performance of existing verification methods based on speaker dependent HMMs with cohort normalization because the errors of the two speaker verification methods are very uncorrelated statistically. Experimental results have shown that when MDD is incorporated into a system that also uses speaker dependent HMMs, the resulting hybrid system has its average equal error rate reduced by 46% compared to cohort normalized speaker independent HMMs. MDD is used with a speaker dependent linear discriminator which has relatively low computational and storage requirements. Thus, the increased performance of a hybrid MDD-Cohort Normalized HMM system may be achieved with minimal increase in computational and data storage assets.

Speaker verification method and apparatus using mixture decomposition

A verification system to determine unknown input speech contains a recognized keyword or consists of speech or other sounds that do not contain any of the keywords. The verification system is designed to operate on the subword level, so that the verification process is advantageously vocabulary independent. Such a vocabulary-independent verifier is achieved by a two-stage verification process comprising subword level verification followed by string level verification. The subword level verification stage verifies each subword segment in the input speech as determined by an Hidden Markov Model recognizer to determine if that segment consists of the sound corresponding to the subword that the HMM recognizer assigned to that segment. The string level verification stage combines the results of the subword level verification to make the rejection decision for the whole keyword. Advantageously, the training of this two-stage verifier is independent of the specific vocabulary set implying that when the vocabulary set is update or changed the verifier need not be retrained and can still be reliably verifying the new set of keywords.

Vocabulary independent discriminative utterance verification for

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.

Rejection of non-digit strings for connected digit speech recognition

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.

Growing community of inventors

Aurora, IL, United States of America

Rafid Antoon Sukkar