Abstract: Techniques and tools for prediction of spectral coefficients in encoding and decoding are described herein. For certain types and patterns of content, coefficient prediction exploits correlation between adjacent spectral coefficients, making subsequent entropy encoding more efficient. For example, an audio encoder predictively codes quantized spectral coefficients in the quantized domain and entropy encodes results of the predictive coding. Or, for a particular quantized spectral coefficient, an audio decoder entropy decodes a difference value, computes a predictor in the quantized domain, and combines the predictor and the difference value.

Abstract: The invention can include a token list generating unit 11 for decomposing a natural language text to be processed into tokens that are components of the natural language text and registering them on a token list, and a token string selecting unit 13 for selecting optimum token strings for composing the natural language text to be processed on the basis of the token list generated by the token list generating unit 11. The token list generating unit 11 registers, on the token list, tokens among the tokens obtained by decomposing the natural language text to be processed except tokens decomposable into smaller tokens according to conditions imposed on the morphological analysis.

Abstract: The invention relates to compression coding and/or decoding of digital signals, in particular by vector variable-rate quantisation defining a variable resolution. For this purpose an impulsion dictionary comprises: for a given dimension, increasing resolution dictionaries imbricated into each other and, for a given dimension, a union of: a totality (D?i<N>) of code-vectors produced, by inserting elements taken in a final set (A) into smaller dimension code-vectors according to a final set of predetermined insertion rules (F1) and a second totality of code-vectors (Y?) which are not obtainable by insertion into the smaller dimension code vectors according to said set of the insertion rules.

Abstract: A voice recognition system and a voice processing system in which a self-repair utterance can be inputted and recognized accurately, as in a conversation in which a human user makes a self-repair utterance. A signal processing unit converts speech voice data into a feature, a voice section detecting unit detects voice sections in the speech voice data, and a priority determining unit selects a voice section that includes a self-repair utterance from among the voice sections according to a priority criterion without using any result of recognizing a speech vocabulary sequence. Priority criteria can include a length of the voice section, signal to noise ratio, chronological order of the voice section as well as speech speed. A decoder calculates a matching score with a recognition vocabulary using the feature of the voice section and an acoustic model.

Abstract: In one exemplary embodiment of the invention, a method is provided for arranging voice feedback to a digital wireless terminal device, which includes a voice-assisted user interface (Voice UI), wherein the terminal device gives a voice feedback corresponding to its state. The terminal device includes memory devices (PPM) for storing the voice feedbacks. In the method, the following stages take place to arrange the voice feedback in connection with the terminal device: one or more voice feedbacks are generated, the generated voice feedbacks are converted into a digital form, the digitalized voice feedbacks are edited with chosen algorithms (ACELP) in order to reduce their file size, and the edited voice feedbacks are stored in a memory (PPM) arranged in connection with the terminal device.

Abstract: As either regular entry or as an assist to the user of existing computer text entry systems, the invention makes possible an alternative method of Chinese character entry by entering a Chinese character assumed by the user to be a rhyme of the character the user desires to enter. Entry methods for such rhyme alternative entry include phonetic and non-phonetic entry of Chinese characters, including keyboard stroke-category input, and handwritten entry using an electronic surface. The invention is not only helpful for entry of difficult Chinese characters but provides an approach to the use of supplementing input methods for most if not all written languages.

Abstract: A writing advisor program (20) receives a proposed text in an author's second language (L2) and determines at least one candidate replacement word for a selected word based on a determined language model (p(c)) and a determined corruption model (p(r|c)). The determined language model reflects correct usage of the text in the second language, independent of the native or first language (L1) of the author, based on (L2) corpora. The determined corruption model is based on some a priori knowledge about probable corruption paths leading the author to realize some inadequate expression in the second language instead of the correct, intended expression. Different types of corruption paths may be used that include bidirectional translations, false-friends, synonyms, common semantic features, second language internal cognates, preposition alternatives, and first language inserts.

Abstract: A system for automating the quality evaluation of a translation. The system may include a computer having a processor and memory device operably connected to one another. A source text in a first language may be stored within the memory device. A target text comprising a translation of the source text into a second language may also be stored within the memory device. Additionally, a plurality of executables may be stored on the memory device and be configured to, when executed by the processor, independently identify a test sample comprising one or more blocks, each comprising a matched set having a source portion selected from the source text and a corresponding target portion selected from the target text.

Abstract: A pitch wave signal creation method as a preliminary process for efficiently coding a speech wave signal having a fluctuated pitch period is provided. A speech signal compressing/expanding apparatus and a speech signal synthesizing apparatus using the method, and a signal processing associated therewith are further provided. The pitch wave creation method of the invention is essentially comprised of a method of detecting the instantaneous pitch period of each pitch wave element of the speech wave signal, and a process of converting a corresponding pitch wave element into a normalized pitch wave element having a predetermined fixed time length by expanding and compressing the pitch wave element on a time axis while retaining its wave pattern based on the each detected instantaneous pitch period. The speech signal having a pitch fluctuation can be compressed in high quality and high efficiency by coding or synthesizing the speech wave signal using the pitch wave signal creation method of the invention.

Abstract: A method and apparatus map a set of vocal tract resonant frequencies, together with their corresponding bandwidths, into a simulated acoustic feature vector in the form of LPC cepstrum by calculating a separate function for each individual vocal tract resonant frequency/bandwidth and summing the result to form an element of the simulated feature vector. The simulated feature vector is applied to a model along with an input feature vector to determine a probability that the set of vocal tract resonant frequencies is present in a speech signal. Under one embodiment, the model includes a target-guided transition model that provides a probability of a vocal tract resonant frequency based on a past vocal tract resonant frequency and a target for the vocal tract resonant frequency. Under another embodiment, the phone segmentation is provided by an HMM system and is used to precisely determine which target value to use at each frame.

Abstract: A method for analyzing audio data (AD) is provided wherein a signature (SAD) is generated based on a feature set (FS) comprising a plurality of time domain related features (TDFk). The signature (SAD) is formed in order to represent a plurality of temporal positions or ranges of a plurality of characteristics of time domain related features (TDFk) within said audio data (AD).

Abstract: A pitch wave signal creation method as a preliminary process for efficiently coding a speech wave signal having a fluctuated pitch period is provided. A speech signal compressing/expanding apparatus and a speech signal synthesizing apparatus using the method, and a signal processing associated therewith are further provided. The pitch wave creation method of the invention is essentially comprised of a method of detecting the instantaneous pitch period of each pitch wave element of the speech wave signal, and a process of converting a corresponding pitch wave element into a normalized pitch wave element having a predetermined fixed time length by expanding and compressing the pitch wave element on a time axis while retaining its wave pattern based on the each detected instantaneous pitch period. The speech signal having a pitch fluctuation can be compressed in high quality and high efficiency by coding or synthesizing the speech wave signal using the pitch wave signal creation method of the invention.

Abstract: A quantizer for quantization of a vector comprises a codevector generator that generates a set of candidate codevectors and a memory for storing an illegal space definition representing illegal vectors. The quantizer also includes a legal status tester that determines legal candidate codevectors among the set of candidate codevectors using the illegal space definition, and a codevector selector that determines a best legal candidate codevector among the one or more legal candidate codevectors. The vector includes parameters relating to a speech and/or audio signal, such as Line Spectral Frequencies (LSFs).

Abstract: Techniques for suppressing noise from a signal comprised of speech plus noise. A first signal detector (e.g., a microphone) provides a first signal comprised of a desired component plus an undesired component. A second signal detector (e.g., a sensor) provides a second signal comprised mostly of an undesired component. The adaptive canceller removes a portion of the undesired component in the first signal that is correlated with the undesired component in the second signal and provides an intermediate signal. The voice activity detector provides a control signal indicative of non-active time periods whereby the desired component is detected to be absent from the intermediate signal. The noise suppression unit suppresses the undesired component in the intermediate signal based on a spectrum modification technique and provides an output signal having a substantial portion of the desired component and with a large portion of the undesired component removed.

Abstract: A code separation/decoding unit restores a vocal tract characteristic sp1 and a vocal source signal r1. A vocal tract characteristic modification unit modifies the vocal tract characteristic sp1 and outputs the modified vocal tract characteristic sp2. In this method, an emphasized vocal tract characteristic sp2 is generated to output by applying formant emphasis, using amplification ratios calculated based on estimated formants, directly to the vocal tract characteristic sp1 for instance. A signal synthesis unit synthesizes the modified vocal tract characteristic sp2 and the vocal source signal r1 to generate and output an output voice, s.

Abstract: A conferencing system is provided that utilizes both time domain signal mixing and direct signal fast transcoding. An exemplary embodiment of the present invention utilizes both time domain signal mixing and direct signal fast transcoding to process a bit-stream from a same channel during a conference.

Abstract: A method and product are provided that identify properly spelled words from an input string. Separate lexical entries are identified for different parts of an input word. Grammatical information associated with one of the lexical entries is examined to determine if it satisfies a grammatical constraint associated with another of the lexical entries. A properly spelled word is formed by combining the separate lexical entries if the grammatical information satisfies the constraint. Under some embodiments of the invention, the separate lexical entries are identified by performing a first search of a lexicon using a first part of the input string and by performing a second search of the lexicon using a second part of the input string.

Abstract: There is provided a speech post-processor for enhancing a speech signal divided into a plurality of sub-bands in frequency domain. The speech post-processor comprises an envelope modification factor generator configured to use frequency domain coefficients representative of an envelope derived from the plurality of sub-bands to generate an envelope modification factor for the envelope derived from the plurality of sub-bands, where the envelope modification factor is generated using FAC=?ENV/Max+(1??), where FAC is the envelope modification factor, ENV is the envelope, Max is the maximum envelope, and ? is a value between 0 and 1, where ? is a different constant value for each speech coding rate. The speech post-processor further comprises an envelope modifier configured to modify the envelope derived from the plurality of sub-bands by the envelope modification factor corresponding to each of the plurality of sub-bands.

Abstract: A decoder for code excited LP encoded frames with both adaptive and fixed codebooks; erased frame concealment uses repetitive excitation plus a smoothing of pitch gain in the next good frame, plus multilevel voicing classification with multiple thresholds of correlations determining linear interpolated adaptive and fixed codebook excitation contributions.

Abstract: A computer-implemented method is disclosed for applying a given paraphrase alternation pattern to an input string. The method includes generating a language model and applying the language model to determine how to apply the given paraphrase alternation pattern to the input string.