Abstract: A system, method and computer program product for classification of an analog electrical signal using statistical models of training data. A technique is described to quantize the analog electrical signal in a manner which maximizes the compression of the signal while simultaneously minimizing the diminution in the ability to classify the compressed signal. These goals are achieved by utilizing a quantizer designed to minimize the loss in a power of the log-likelihood ratio. A further technique is described to enhance the quantization process by optimally allocating a number of bits for each dimension of the quantized feature vector subject to a maximum number of bits available across all dimensions.

Abstract: A system and method for identifying audio command prompts for use in a voice response environment is provided. A signature is generated for audio samples each having preceding audio, reference phrase audio, and trailing audio segments. The trailing segment is removed and each of the preceding and reference phrase segments are divided into buffers. The buffers are transformed into discrete fourier transform buffers. One of the discrete fourier transform buffers from the reference phrase segment that is dissimilar to each of the discrete fourier transform buffers from the preceding segment is selected as the signature. Audio command prompts are processed to generate a discrete fourier transform. Each discrete fourier transform for the audio command prompts is compared with each of the signatures and a correlation value is determined. One such audio command prompt matches one such signature when the correlation value for that audio command prompt satisfies a threshold.

Abstract: A machine-readable medium and a network device are provided for speech-to-text translation. Speech packets are received at a broadband telephony interface and stored in a buffer. The speech packets are processed and textual representations thereof are displayed as words on a display device. Speech processing is activated and deactivated in response to a command from a subscriber.

Abstract: A system and method for efficiently transcribing verbal messages transmitted over the Internet (or other network) into text. The verbal messages are initially checked to ensure that they are in a valid format and include a return network address, and if so, are processed either as whole verbal messages or split into segments. These whole verbal messages and segments are processed by an automated speech recognition (ASR) program, which produces automatically recognized text. The automatically recognized text messages or segments are assigned to selected workbenches for manual editing and transcription, producing edited text. The segments of edited text are reassembled to produce whole edited text messages, undergo post processing to correct minor errors and output as an email, an SMS message, a file, or an input to a program. The automatically recognized text and manual edits thereof are returned as feedback to the ASR program to improve its accuracy.

Abstract: A method, article of manufacture, and apparatus for presenting an auditory recording having associated data representing at least one term identified in the recording is disclosed. In an embodiment, this comprises providing a visual representation of the term, providing a link associated with an occurrence of the term in the recording, and when the link is selected, playing a portion of the recording corresponding to the occurrence of the term. A portion of the recording following the portion corresponding to the occurrence of the term may be played.

Abstract: A concept obtaining unit obtains, for each example set stored in an example storage unit, a first concept of a phrase included in an example in the first language and a second concept of a phrase included in an example in the second language from a concept storage unit. A determining unit determines that an example set including an unmatched concept between first concepts and second concepts is not applicable. An example set searching unit searches for an example set that includes an example in the first language that is analogous to or matches an input sentence. An output controlling unit outputs an example in the second language of the example sets from which the example set that is determined as inapplicable is deleted, as a translation result.

Abstract: A down-sampler 101 down-samples the sampling rate of an input signal from sampling rate FH to sampling rate FL. A base layer coder 102 encodes the sampling rate FL acoustic signal. A local decoder 103 decodes coding information output from base layer coder 102. An up-sampler 104 raises the sampling rate of the decoded signal to FH. A subtracter 106 subtracts the decoded signal from the sampling rate FH acoustic signal. An enhancement layer coder 107 encodes the signal output from subtracter 106 using a decoding result parameter output from local decoder 103.

Abstract: In an information detecting apparatus (1), a speech kind discrimination unit (11) discriminates and classifies an audio signal at an information source into kind (category) such as music or speech, etc. on a predetermined time basis, and a memory unit/recording medium (13) records discrimination information thereof. A discrimination frequency calculating unit (15) calculates, on a predetermined time basis, discrimination frequency every kind at a predetermined time period longer than the time unit.

Abstract: A method for sending data to a sight impaired user, the method comprising, receiving data from a data resource, determining whether the data is compatible with a Symbian API, transcoding the data into a first format compatible with the Symbian API, determining whether the data is compatible with a TALKS filter, transcoding the data into a second format compatible with the TALKS filter, determining whether the data is usable by a sight impaired user, transcoding the data into a third format usable by a sight impaired user responsive to determining that the data is not usable by a sight impaired user, converting a data type definition associated with the data into a format compatible with a user profile, sending the received data to a user mobile device, wherein the mobile device is operative to convert the data into an audible output.

Abstract: A non-intrusive signal quality assessment apparatus includes a feature vector calculator that determines parameters representing frames of a signal and extracts a collection of per-frame feature vectors (?;(n)) representing structural information of the signal from the parameters. A frame selector preferably selects only frames (?\with a feature vector (?;(n)) lying within a predetermined multi-dimensional window (?). Means determine a global feature set (?) over the collection of feature vectors (?;(n)) from statistical moments of selected feature vector components ((1^,02, . . . O11). A quality predictor predicts a signal quality measure (Qj from the global feature set (?)).

Abstract: Apparatus and method for generating high quality synthesized speech having smooth waveform concatenation. The apparatus includes a pitch frequency calculation section, a pitch synchronization position calculation section, a unit waveform storage, a unit waveform selection section, a unit waveform generation section, and a waveform synthesis section. The unit waveform generation section includes a conversion ratio calculation section, a sampling rate conversion section, and a unit waveform re-selection section. The conversion ratio calculation section calculates a sampling rate conversion ratio from the pitch information and the position of pitch synchronization, and the sampling rate conversion section converts the sampling rate of the unit waveform, delivered as input, based on the sampling rate conversion ratio.

Abstract: A bandwidth extension system extends the bandwidth of an acoustic signal. By shifting a portion of the signal by a frequency value, the system generates an upper bandwidth extension signal. An extended bandwidth acoustic signal may be generated from the acoustic signal, the upper bandwidth extension signal, and/or a lower bandwidth extension signal.

Abstract: Methods for analyzing, evaluating, and controlling risk of errors in language translation of medical device labeling are disclosed. The disclosed methods include identifying the risk level of the device; identifying the safety function(s) of the content that is translated; evaluating risks associated with the translation process; and analyzing this risk information and applying it in the selection of resources and in the design and execution of processes, to effectively mitigate the risk of safety related translation errors in labeling for medical devices.

Abstract: A method, device and system for signal encoding and decoding, the method comprising: encoding a core layer signal to obtain a core layer signal code; selecting an enhancement sample point that requires enhancement layer signal encoding according to the core layer signal code and the number of bits that can be used by an enhancement layer; obtaining an enhancement layer signal code of the enhancement sample point; and outputting a bit stream, where the bit stream includes the core layer signal code and the enhancement layer signal code. In embodiments of the present invention, according to the number of bits that can be used by the enhancement layer, the enhancement sample point that requires enhancement layer signal encoding is selected; the enhancement layer signal of the selected enhancement sample point is encoded and decoded; when no sufficient bits are available for the enhancement layer, the enhancement quality of the core layer can be improved.

Abstract: A method (and structure) of extracting information from text, includes parsing an input sample of text to form a parse tree and using user inputs to define a machine-labeled learning pattern from the parse tree.

Abstract: Methods and apparatuses for encoding a signal and decoding a signal and a system for encoding and decoding are provided. The method for encoding a signal includes performing a classification decision process on high frequency signals of input signals, adaptively encoding the high frequency signals according to the result of the classification decision process, and outputting a bitstream including codes of low frequency signals of the input signals, adaptive codes of the high frequency signals, and the result of the classification decision process. The classification decision process is performed on the high frequency signals, and adaptive encoding or adaptive decoding is performed according to the result of the classification decision process, so the quality of voice and audio output signals is improved.

Abstract: Systems and methods are disclosed for searching across multi-lingual information. A user makes a query in a first language, and a group of documents that were previously machine-translated into the first language are searched for information responsive to the query. Contextual information derived can be used to improve the accuracy of the machine translation. Responsive documents are returned to the user. Alternatively, a query provided in a user's language may be translated into one or more other languages. Documents written in these languages can then be searched for information responsive to the appropriate translated query. Responsive documents can be translated into the user's language prior to providing them to the user.

Abstract: When performing audio communication by using different encoding/decoding methods, a code obtained by encoding audio by a certain method is converted into a code decodable by another method with a high audio quality and a small calculation amount. In a code conversion device for converting a first code string into a second code string, an audio decoding circuit acquires a first linear prediction coefficient and excitation signal information from the first code string and drives the filter having the first linear prediction coefficient by the excitation signal obtained from the excitation signal information, thereby creating a first audio signal. A fixed codebook code generation circuit uses the fixed codebook information and minimizes the distance between the second audio signal generated from the information obtained from the second code string and the first audio signal, thereby obtaining the fixed codebook information in the second code string.

Abstract: A method for supporting an encoding of an audio signal is shown, wherein at least a first and a second coder mode are available for encoding a section of the audio signal. The first coder mode enables a coding based on two different coding models. A selection of a coding model is enabled by a selection rule which is based on signal characteristics which have been determined for a certain analysis window. In order to avoid a misclassification of a section after a switch to the first coder mode, it is proposed that the selection rule is activated only when sufficient sections for the analysis window have been received. The invention relates equally to a module in which this method is implemented, to a device and a system comprising such a module and to a software program product including a software code for realizing the proposed method.

Abstract: A system and method for enabling two computer systems to communicate over an audio communications channel, such as a voice telephony connection. Such a system includes a software application that enables a user's computer to call, interrogate, download, and manage a voicemail account stored on a telephone company's computer, without human intervention. A voicemail retrieved from the telephone company's computer can be stored in a digital format on the user's computer. In such a format, the voicemail can be readily archived, or even distributed throughout a network, such as the Internet, in a digital form, such as an email attachment. Preferably a computationally efficient audio recognition algorithm is employed by the user's computer to respond to and navigate the automated audio menu of the telephone company's computer.