Abstract: This invention is related to tandem free operation (TFO) in mobile cellular systems. The present invention implements a tandem free operation by using a special feedback loop which makes the decoded parameters available, performs the comfort noise insertion and bad frame handling operations, produces the parameter quantisation indices corresponding to the output of these operations, and synchronises the speech encoders and the speech decoders in the transmission path from the uplink mobile station to the downlink mobile station. This functionality is realized by partly decoding and re-encoding the parameters and synchronising and resetting the quantiser prediction memories in a specific manner. A basic idea of the invention is, that during BFH and CNI processes, a re-encoding block produces models of encoded speech parameters from the BFH/CNI processed speech parameters. These models of encoded speech parameters are then transmitted to the receiving end.

Abstract: In this invention dialogue states for a dialogue model are created using a training corpus of example human—human dialogues. Dialogue states are modelled at the turn level rather than at the move level, and the dialogue states are derived from the training corpus. The range of operator dialogue utterances is actually quite small in many services and therefore may be categorized into a set of predetermined meanings. This is an important assumption which is not true of general conversation, but is often true of conversations between telephone operators and people. Phrases are specified which have specific substitution and deletion penalties, for example the two phrases “I would like to” and “can I” may be specified as a possible substitution with low or zero penalty. Thus allows common equivalent phrases are given low substitution penalties. Insignificant phrases such as ‘erm’ are given low or zero deletion penalties.

Abstract: A special relation is formed between an owner and a virtual pet and a sense for feeling a pet more similar to a true pet is produced. Voice inputted from a microphone 22 is recognized by a recognizing part 20. Then, a speaker data base 12 is referred to to identify a speaking individual. In the data base 12, prescribed words and phrases are registered and events corresponding to the words and phrases are stored in an event list 31. If the words and phrases spoken by the individual to a pet satisfy an event generating condition, events (crying, swinging a tail, etc.) corresponding to the recognized words and phrases will be performed.

Abstract: An automated speech recognition filter is disclosed. The automated speech recognition filter device provides a speech signal to an automated speech platform that approximates an original speech signal as spoken into a transceiver by a user. In providing the speech signal, the automated speech recognition filter determines various models representative of a cumulative signal degradation of the original speech signal from various devices along a transmission signal path and a reception signal path between the transceiver and a device housing the filter. The automated speech platform can thereby provide an audio signal corresponding to a context of the original speech signal.

Abstract: A method and apparatus for transient detection and time-scaling an audio signal detects transients and scales only intervals located between transients to avoid artifacts. In one embodiment, the transient detection process compares frequency characteristic energy between succeeding windows of the audio signal and calculates values of an energy curve where the energy increases. Transients are detected at maxima of the energy curve.

Abstract: An improved forward error correction (FEC) technique for coding speech data provides an encoder module which primary-encodes an input speech signal using a primary synthesis model to produce primary-encoded data, and redundant-encodes the input speech signal using a redundant synthesis model to produce redundant-encoded data. A packetizer combines the primary-encoded data and the redundant-encoded data into a series of packets and transmits the packets over a packet-based network, such as an Internet Protocol (IP) network. A decoding module primary-decodes the packets using the primary synthesis model, and redundant-decodes the packets using the redundant synthesis model. The technique provides interaction between the primary synthesis model and the redundant synthesis model during and after decoding to improve the quality of a synthesized output speech signal. Such “interaction,” for instance, may take the form of updating states in one model using the other model.

Abstract: A method and system that combines voice recognition engines and resolves differences between the results of individual voice recognition engines using a mapping function. Speaker independent voice recognition engines and speaker-dependent voice recognition engines are combined. Hidden Markov Model (HMM) engines and Dynamic Time Warping (DTW) engines are combined.

Abstract: Methods and apparatus for facilitating speaker recognition, wherein, from target data that is provided relating to a target speaker and background data that is provided relating to at least one background speaker, a set of cohort data is selected from the background data that has at least one proximate characteristic with respect to the target data. The target data and the cohort data are then combined in a manner to produce at least one new cohort model for use in subsequent speaker verification. Similar methods and apparatus are contemplated for non-voice-based applications, such as verification through fingerprints.

Abstract: A communication system is disclosed in one embodiment of the present invention to include an encoder circuit responsive to an audio signal for performing compression on the audio signal and adaptive to generate an audio output signal based upon the compressed audio signal, the encoder circuit for sampling the audio signal to generated sampled signals, each sampled signals having a real and an imaginary component associated therewith, each sampled signal having an energy and a phase defined within a current block and each sampled signal being transformed to have a real and an imaginary component, a previous block preceding the current block and a block preceding the previous block, the encoder circuit for calculating the phase of the samples of the current block using the real and the imaginary components of the samples of the previous block and the block preceding the previous block, wherein calculations for determining the unpredictability measure is reduced by avoiding trigonometric calculations of the samp

Abstract: According to the present invention, there is developed a proprietary technology for compressing the window tables of audio coders to ⅛ their original size (or less) without any loss of quality. This technology can be applied to all transform based audio coders, or any audio coder that uses a windowing stage. The novel technique for reducing storage requirements for the window tables of audio coders is based on multiple differentiation. Since the difference between any two adjacent samples in the first difference signal is small, so it is more efficient to store this difference. This technique can be carried out several more times, until the returns get smaller, and the computational requirements to “undo” the compression go up. The optimum number of times to differentiate is dependent on the particular application and the window shape.

Abstract: According to one aspect of the invention, a method is provided in which audio samples representing an input audio signal are received. The input audio samples are transformed into a vector of spectral values in a frequency domain. A value of a quantizing parameter is determined that satisfies one or more criteria based, at least in part, on a modified Newtonian search process, the determined value of the quantizing parameter being used to quantize the respective vector of spectral values to generate a vector of quantized values.

Abstract: In a sound synthesizer, a noise adder generates a noise signal having a frequency band of 3,400 to 4,600 Hz, adjusts the gain of the noise signal, and adds the gain-adjusted noise signal to an excitation source after being filled with zeros by a zero-filling circuit, thereby providing a wide-band excitation source which is rather flat. The signal gain is adjusted by determining a narrow-band excitation source or a power of the wide-band excitation source after being filled with zeros and fitting the gain to the narrow-band excitation source or the power.

Abstract: An apparatus, method and system provide for caller input rate control for automatic speech recognition (ASR) components within interactive communication systems. The various embodiments provide a concentrator functionality to increase the capacity of ASR systems, and provide a delay functionality to continue to provide service to callers during congestion or overload conditions. The delay functionality provides various associated delay modes, including the insertion of silent periods within messages or prompts played to a caller, and providing increased message duration. The preferred method embodiment determines a usage level of a plurality of ASR input channels, and when the usage level is greater than a first predetermined threshold, provides an associated delay mode for a message output on an output channel of the plurality of output channels.

Abstract: In the digital player, a decoder, having at least first and second decoding functions, identifies a type of digital data output from a data storage medium. Based on the identification, the decoder selects one of the first and second decoding functions, and decodes the output digital data using the selected decoding function. A converter converts the decoded digital data to analog. To store digital data on the data storage medium, an encoder encodes a first type of digital data at a first compression rate, and stores the encoded first type of digital data on the data storage medium, which stores digital data of a second type encoded at a second compression rate. The first compression rate is higher than the second compression rate. A selector, having at least a first and second input for the first type of digital data, selectively outputs the first type of digital data received at one of the first and second inputs to the encoder.

Abstract: A method for performing audible fast-forward or reverse of audio content represented in a compressed format, such as, but not limited to, MPEG-1 Layer 3 (MP3) or MPEG-2 Advance Audio Coding (AAC) employs a fast-forward controller which performs fast-forward or reverse by repeatedly skipping forward or reverse in the compressed audio data stream, retrieving a block of data, and then splicing these data blocks back together. A decoder is then used to decode each of these blocks, to detect when a block switch has occurred (a splice in the data stream), and to quickly resynchronize at each transition. Hierarchical or multiplexed data streams may be decoded using a cascade of decoders each employing this technique. The decoder uses a robust sync search for performing resynchronization and error recovery.

Abstract: A digital cordless phone system and a communication method for improving the distance of speech communication using error concealment are provided. The digital cordless phone system has a base unit and a remote unit, and each of the base and remote units has a first codec, a data processing unit, a controller, a modem and a switch. The first codec encodes voice data in a first encoding mode, and decodes the data encoded in the first encoding mode in a first decoding mode.

Abstract: An input signal is time-frequency transformed, then the frequency-domain coefficients are divided into coefficient segments of about 100 Hz width to generate a sequence of coefficient segments, and the sequence of coefficient segments is split into subbands each consisting of plural coefficient segments. A threshold value is determined based on the intensity of each coefficient segment in each subband. The intensity of each coefficient segment is compared with the threshold value, and the coefficient segments are classified into low- and high-intensity groups. The coefficient segments are quantized for each group, or they are flattened respectively and then quantized through recombination.

Abstract: A vector quantizing apparatus, a decoding apparatus, a vector quantization method, and a decoding method are provided. Upon encoding of a speech signal by the vector quantization apparatus and method, the advantages of vector quantization are maximized by quantizing the speech signal using KLT-based classified codebooks and the eigenvalues and eigenvectors of the speech signal. The vector quantization apparatus includes a codebook group, a Karhunen-Loéve Transform (KLT) unit, first and second selection units and a transmission unit. The codebook group has a plurality of codebooks that store the code vectors for a speech signal, and the codebooks are classified using KLT domain statistics for the speech signal. The KLT unit transforms an input speech signal to a KLT domain. The first selection unit selects an optimal codebook from the codebooks in the codebook group on the basis of the eigenvalue set of the covariance matrix of the input speech signal obtained by KLT.

Abstract: Improvements in speech recognition systems are achieved by considering projections of the high dimensional data on lower dimensional subspaces, subsequently by estimating the univariate probability densities via known univariate techniques, and then by reconstructing the density in the original higher dimensional space from the collection of univariate densities so obtained. The reconstructed density is by no means unique unless further restrictions on the estimated density are imposed. The variety of choices of candidate univariate densities as well as the choices of subspaces on which to project the data including their number further add to this non-uniqueness. Probability density functions are then considered that maximize certain optimality criterion as a solution to this problem. Specifically, those probability density function's that either maximize the entropy functional, or alternatively, the likelihood associated with the data are considered.