Abstract: A sound encoder and sound decoder that encode and decode, respectively, variable length codes on a frame by frame basis, the coding including main codes and auxiliary codes in which auxiliary codes are multiplexed or demultiplexed in a same fixed order to determine the order of multiplexing and demultiplexing the main codes which are used to determine where the codes are to be placed in the sound code.

Abstract: According to an embodiment of the invention, a physical location of a mobile device is determined, and a determination is made that a subject device is available for command via the mobile device based at least in part on the physical location of the mobile device. Information regarding voice recognition capability of the subject device is transferred to the mobile device. A voice command is received by the mobile device, the voice command is interpreted, and an instruction is provided to the subject device based at least in part on the voice command.

Abstract: An apparatus for processing CELP-based frames includes a first module for extracting a CELP parameter from a source codec, a second module coupled to the first module adapted to interpolate between a CELP parameter of the source codec and a destination codec, the CELP parameter being selected from a group consisting of a frame size, a subframe size, and a sampling rate, a third module coupled to the second module adapted to map the CELP parameter from the source codec to a CELP parameter of the destination codec, a fourth module coupled to the third module adapted to construct a destination output CELP frame based upon the CELP parameter from the destination codec, and a controller coupled the first, second, third and fourth modules, adapted to oversee an operation of the modules, adapted to receive instructions from an external application, and adapted to provide status information to the external application.

Abstract: A distributed speech recognition system includes a noise floor estimator to provide a noise floor estimate to a feature extractor which provides a parametric representation of the noise floor estimate. An encoder is included to to generate an encoded parametric representation of the noise floor estimate. A front-end controller is also included to determine when at least one of the noise floor estimator, the feature extractor, and the encoder is to be turned on or off and to determine when the noise floor estimator is to provide the noise floor estimate to the feature extractor. Additionally, a decoder is included to generate a decoded parametric representation of the noise floor estimate. A noise model generator creates a statistical model of noise feature vectors based on the decoded parametric representation of the noise floor estimate.

Abstract: Recognizing a stream of speech received as speech vectors over a lossy communications link includes constructing for a speech recognizer a series of speech vectors from packets received over a lossy packetized transmission link, wherein some of the packets associated with each speech vector are lost or corrupted during transmission. Each constructed speech vector is multi-dimensional and includes associated features. Potentially corrupted features within the speech vector are indicated to the speech recognizer when present. Speech recognition is attempted at the speech recognizer on the speech vectors when corrupted features are present. This recognition may be based only on certain or valid features within each speech vector. Retransmission of a missing or corrupted packet is requested when corrupted values are indicated by the indicating step and when the attempted recognition step fails.

Abstract: Auditory-articulatory analysis for use in speech quality assessment. Articulatory analysis is based on a comparison between powers associated with articulation and non-articulation frequency ranges of a speech signal. Neither source speech nor an estimate of the source speech is utilized in articulatory analysis. Articulatory analysis comprises the steps of comparing articulation power and non-articulation power of a speech signal, and assessing speech quality based on the comparison, wherein articulation and non-articulation powers are powers associated with articulation and non-articulation frequency ranges of the speech signal.

Abstract: A decoder (10) decodes compressed data. A memory (44) stores the compressed data and stores operating data and operating code for a plurality of decompression algorithms requiring different amounts of memory for the operating data and operating code and requiring different amounts of memory to store compressed data corresponding to a predetermined amount of uncompressed data. A processor (42) is arranged to select one of the decompression algorithms, to allocate an amount of the memory for storing compressed data and operating data and operating code depending on the decompression algorithm selected and to decode the compressed data stored in the allocated amount of memory.

Abstract: An apparatus and method for noise reduction employ a first processor having one or more channels, each channel comprising a respective first processor filter, and each channel configured to receive a respective one of one or more input signals. The first processor is configured to provide an intermediate output signal. The apparatus and method further employ a second processor including a second processor filter configured to receive the intermediate output signal and to provide a noise-reduced output signal. The apparatus and method further employ a first adaptation processor coupled to the first processor and a second adaptation processor coupled to the second processor. In some embodiments, an echo canceling processor reduces an echo portion associated with the noise-reduced output signal. In some embodiments, a response of the first filter portion and of the second filter portion are dynamically adapted.

Abstract: A speech-to-text conversion system. The two-way speech recognition and dialect system comprises a computer system, an attached microphone assembly, and speech-to-text conversion software. The two-way speech recognition and dialect system includes a database of dialectal characteristics and queries a user to determine their likely dialect. The system uses this determination to reduce the time for the system to reliably transcribe a user's speech into text and to anticipate dialectal word usage. In another embodiment of the invention, the two-way speech recognition and dialect system is capable of transcribing the speech of multiple speakers while distinguishing between the different speakers and identifying the text belonging to each speaker.

Abstract: Quantization matrices facilitate digital audio encoding and decoding. An audio encoder generates and compresses quantization matrices; an audio decoder decompresses and applies the quantization matrices. For example, the audio encoder includes a multi-channel transformer operable to output multi-channel audio data in jointly coded channels and a program module for generating a single quantization matrix for weighting all of the jointly coded channels. In one such example, the program module computes the single quantization matrix from an aggregation of pattern information for all of the jointly coded channels, and the aggregation of pattern information is an aggregate excitation pattern.

Abstract: A voice intensifier capable of reducing abrupt changes in the amplification factor between frames and realizing excellent sound quality with less noise feeling by dividing input voices into the sound source characteristic and the vocal tract characteristic, so as to individually intensify the sound source characteristic and the vocal tract characteristic and then synthesize them before being output.

Abstract: A method for detecting pauses in speech signals is disclosed in which the frequency spectrum is divided into two or more sub-bands. Samples of the signals on the sub-bands are stored at intervals, the energy levels of the sub-bands are determined on the basis of the stored samples, a power threshold value (thr) is determined, and the energy levels of the sub-bands are compared with said power threshold value (thr) . A subband minimum is set and a detection time limit is set so that, in a noise situation, a speech pause can be verified by checking to determine if each pause detected remains for the duration of the detection time limit and if a pause is detected in at least said minimum subbands.

Abstract: A method and system are provided for removing discontinuities associated with synthesizing a corrupted frame output from a decoder including one or more predictive filters. The corrupted frame is representative of one segment of a decoded signal. The method comprises copying a first number of stored samples of the decoded signal in accordance with a time lag and a scaling factor, and calculating a first number of ringing samples output from at least one of the filters.

Abstract: Quantization matrices facilitate digital audio encoding and decoding. An audio encoder generates and compresses quantization matrices; an audio decoder decompresses and applies the quantization matrices. For example, the audio encoder generates a quantization matrix including weighting factors and processes a set of weighting factors according to a parametric model to switch between a direct representation and a parametric representation of the set of weighting factors, where the parametric representation of the set of weighting factors accounts for audibility of distortion according to a model of human auditory perception. In another example, an audio encoder receives a band weight representation of a ciuantization matrix and compresses the band weight representation of the quantization matrix using linear predictive coding, wherein the compressing includes computing pseudo-autocorrelation values for the quantization matrix.

Abstract: The present invention is a method and system for identifying or realizing an output sequence using a grammar that can be used to encode semantic representation of the output. A goal incorporating a semantic representation is obtained and rules in the grammar are identified as having semantic representation components that can be matched with semantic representation components of the goal or portions thereof. The output sequence is realized based on the rules identified.

Abstract: A comprehensive system is provided for designing a voice activated user interface (VA UI) having a semantic and syntactic structure adapted to the culture and conventions of spoken language for the intended users. The system poses, to at least one respondent, a hypothetical task to be performed; asks each of the at least one respondent for a word that the respondent would use to command the hypothetical task to be performed; receives, from each of the at least one respondent, a command word; develops a list of command words from the received command word; and rejects the received command word, if the received command word is acoustically similar to another word in the list of command words. The approach is general across languages and encompasses universal variables of language and culture. Also provided are prompting grammar and error handling methods adapted to such user interfaces.

Abstract: A data reproducing apparatus according to the present invention enables a recorder to rewrite recorded contents of a memory card. A digital signal processing section (DSP) detects a compression system for compressed data recorded in the memory card. A central processing unit (CPU) detects whether or not the memory card records a decoding file corresponding to the detected compression system. When such decoding file is not detected, internal memory stores data indicating the undetected decoding file.

Abstract: To increase the recognition rate and quality in a process of recognizing speech an approximative set of pronunciation rules (APR) for a current pronunciation (CP) of a current speaker is determined in a given pronunciation space (PS) and then applied to a current pronunciation lexicon (CL) so as to perform a speaker specific adaptation of said current lexicon (CL).

Abstract: In a voice pitch normalization device equipped in a voice recognition device VRAp for recognizing an incoming command voice Sva uttered by any speaker, and used to normalize the incoming command voice to be in an optimal pitch for voice recognition, a target voice generator produces a target voice signal by changing the incoming command voice Svd on the basis of a predetermined degree. A probability calculator calculates a probability indicating a degree of coincidence among the target voice signal and a plurality of words in sample data. A voice pitch changer repeatedly changes the target voice signal in voice pitch until a maximum probability becomes a predetermined probability or greater.

Abstract: A system and method facilitating training machine learning systems utilizing sequential conditional generalized iterative scaling is provided. The invention includes an expected value update component that modifies an expected value based, at least in part, upon a feature function of an input vector and an output value, a sum of lambda variable and a normalization variable. The invention further includes an error calculator that calculates an error based, at least in part, upon the expected value and an observed value. The invention also includes a parameter update component that modifies a trainable parameter based, at least in part, upon the error. A variable update component that updates at least one of the sum of lambda variable and the normalization variable based, at least in part, upon the error is also provided.