Lucent Technologies Inc.

At&t Bell Laboratories

American Telephone & Telegraph Co., At&t Bell Laboratories

American Telephone and Telegraph, Co.

Richard H Ketchum

Willem Bastiaan Kleijn

Anand Rangaswamy Setlur

David Lynn Thomson

Daniel J Krasinski

Rathinavelu Chengalvarayan

Walter T Hartwell

Edward C Bronson

Jeffrey Wayne Daugherty

Thomas E Jacobs

Echoes caused by discontinuities in a telecommunications transmission lines cause double talk which cause divergence problems with echo cancellers. Divergence problems in echo cancellers cause considerable problems in interactive caller response systems, they cause less problems if all parties to a call are human. One of the biggest problems is the effect of the echoes on automatic speech recognition systems. The echo canceller method and system presented cancels echoes to reduce their interference with ASR and yet provides stability in the presence of double talk.

Robust double-talk detection and recovery in a system for echo cancelation

A system and method provide ASR talkoff suppression in a prompt-and collect voice transaction system in which a prompt signal is sent and an input signal is received. A comparison is made of a characteristic of the prompt signal and the input signal. Processing of the input signal to reduce the likelihood of an ASR response thereto is performed if the result of the comparison satisfies a predetermined criterion.

ASR talkoff suppressor

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.

HMM-based echo model for noise cancellation avoiding the problem of false triggers

A first validation circuit utilizes residual energy unaccounted for by a linear predictive coding model for a specified order of model as a criteria on which to make a validity determination of whether a valid tone or digit has been received. A second validation circuit operating in conjunction with the first validation circuit utilizes discrete Fourier transforms at the center and adjacent frequencies to energy peaks associated with tones. A ratio of the peak energy to the adjacent energies is utilized in combination with corresponding thresholds to make a validity determination. The combination of the first and second validation circuit provides a high level of confidence that a particular tone or digit has been detected.

Detection of tones while minimizing incorrect identification of other

An exemplary CELP coder where gain adaptation is performed using previous gain values in conjunction with an entry in a table comprising the logarithms of the root-mean-squared values of the codebook vectors, to predict the next gain value. Not only is this method less complex because the table entries are determined off-line, but in addition the use of a table at both the encoder and the decoder allows fixed-point/floating-point interoperability requirements to be met.

Backward gain adaptation method in code excited linear prediction coders

Apparatus for encoding speech using a code excited linear predictive (CELP) encoder using a virtual searching technique during speech transitions such as from unvoiced to voiced regions of speech. The encoder compares candidate excitation vectors stored in a codebook with a target excitation vector representing a frame of speech to determine the candidate vector that best matches the target vector by repeating a first portion of each candidate vector into a second portion of each candidate vector. For increased performance, a stochastically excited linear predictive (SELP) encoder is used in series with the adaptive CELP encoder. The SELP encoder is responsive to the difference between the target vector and the best matched candidate vector to search its own overlapping codebook in a recursive manner to determine a candidate vector that provides the best match. Both of the best matched candidate vectors are used in speech synthesis.

Code excited linear predictive vocoder using virtual searching

Apparatus for encoding speech using a code excited linear predictive (CELP) encoder using a recursive computational unit. In response to a target excitation vector that models a present frame of speech, the computational unit utilizes a finite impulse response linear predictive coding (LPC) filter and an overlapping codebook to determine a candidate excitation vector from the codebook that matches the target excitation vector after searching the entire codebook for the best match. For each candidate excitation vector accessed from the overlapping codebook, only one sample of the accessed vector and one sample of the previously accessed vector must have arithmetic operations performed on them to evaluate the new vector rather than all of the samples as is normal for CELP methods. For increased performance, a stochastically excited linear predictive (SELP) encoder is used in series with the adaptive CELP encoder. The SELP encoder is responsive to the difference between the target excitation vector and the best matched candidate excitation vector to search its own overlapping codebook in a recursive manner to determine a candidate excitation vector that provides the best match. Both of the best matched candidate vectors are used in speech synthesis.

Code excited linear predictive vocoder

A speech analyzer and synthesizer system using a sinusoidal encoding and decoding technique for voiced frames and noise excitation or multipulse excitation for unvoiced frames. For voiced frames, the analyzer transmits the pitch, values for a subset of offsets defining differences between harmonic frequencies and a fundamental frequency, total frame energy, and linear predictive coding, LPC, coefficients. The synthesizer is responsive to that information to determine the harmonic frequencies from the offset information for a subset of the harmonics and to determine the remaining harmonics from the fundamental frequency. The synthesizer then determines the phase for the fundamental frequency and harmonic frequencies and determines the amplitudes of the fundamental and harmonics using the total frame energy and the LPC coefficients. Once the phase and amplitudes have been determined for the fundamental and harmonic frequencies, the synthesizer performs a sinusoidal analysis. In another embodiment, the remaining harmonic frequencies are determined by calculating the theoretical harmonic frequencies for the remaining harmonic frequencies and grouping these theoretical frequencies into groups having the same number as the number of offsets transmitted. The offsets are then added to the corresponding theoretical harmonics of each of the groups of the remaining harmonic frequencies to generate the remaining harmonic frequencies. In a third embodiment, the offset signals are randomly permuted before being added to the groups of theoretical frequencies to generate the remaining harmonic frequencies.

Growing community of inventors

Wheaton, IL, United States of America

Richard H Ketchum