Abstract: Methods of document expansion for a speech retrieval document by a recognizer. A database of vectors of automatic transcriptions of documents is accessed and the vectors are truncated by removing all terms that are not recognizable by the recognizer to create truncated vectors. Terms in the vectors are then weighted to associate the truncated vectors with the untruncated vectors. Terms not recognized by the recognizer are then added back to the weighted, truncated vectors. The retrieval effectiveness may then be measured.

Abstract: Operations for weighted and non-weighted multi-tape automata are described for use in natural language processing tasks such as morphological analysis, disambiguation, and entity extraction.

Abstract: A system for rehabilitation of a hearing disorder which comprises at least one acoustic sensor for picking up an acoustic signal and converting it into an electrical audio signal, an electronic signal processing unit for audio signal processing and amplification, an electrical power supply unit which supplies individual components of the system with current, and an actuator arrangement which is provided with one or more electroacoustic, electromechanical or purely electrical output-side actuators or any combination of these actuators for stimulation of damaged hearing, wherein the signal processing unit has a speech analysis and recognition module and a speech synthesis module.

Abstract: The specification discloses a computer-based system and method for enhancing language listening comprehension. The system and method perform analyses according to the answers entered by the learner. The analysis result determines whether to increase or lower the voice-playing speed and whether to increase or decrease the problem difficulty.

Abstract: A system and method of controlling the movement of a virtual agent while the agent is listening to a human user during a conversation is disclosed. The method comprises receiving speech data from the user, performing a prosodic analysis of the speech data and controlling the virtual agent movement according to the prosodic analysis.

Abstract: An initial number of bits associated with an initial common scale factor is determined, an initial increment is computed using the initial number of bits and a target number of bits, and the initial scale factor is incremented by the initial increment. Further, the incremented common scale factor is adjusted based on the target number of bits, and individual scale factors are computed based on the adjusted common scale factor and allowed distortion. If a current number of bits associated with the computed individual scale factors exceeds the target number of bits, the adjusted common scale factor is modified until a resulting number of bits no longer exceeds the target number of bits.

Abstract: A noise suppression device calculates a subband SN ratio calculation based on a noise likeness signal, an input signal spectrum and a subband-based estimated noise spectrum. The device calculates a subband-based input signal average spectrum, calculates a subband-based mixture ratio of the subband-based estimated noise spectrum to the subband-based input signal average spectrum on the basis of the noise likeness signal, and calculates the subband-based SN ratio on the basis of the subband-based estimated noise spectrum, the subband-based input signal average spectrum and the mixture ratio.

Abstract: A system and method of controlling the movement of a virtual agent while the agent is listening to a human user during a conversation is disclosed. The method comprises receiving speech data from the user, performing a prosodic analysis of the speech data and controlling the virtual agent movement according to the prosodic analysis.

Abstract: Topicality scores are determined for a number of phrasal expressions in documents. Phrasal expressions may be noun phrases, with or without corresponding prepositional phrases, subject-verb pairs, and verb-object pairs. The documents describe some topic or multiple topics. Techniques can be used to determined how the phrasal expression compares with the topic or topics being described in the documents. Specificities are determined for the phrasal expressions. Techniques may be used to determine whether phrasal expressions are more or less specific than other phrasal expressions. An order is determined for the phrasal expressions by using the topicality scores and the specificities. The order may be represented as a phrasal expression tree, for example. The phrasal expression tree may be displayed to a user, and the user can navigate through the phrasal expression tree, and therefore through the one or more documents.

Abstract: Prior to embedding a watermark in an audio signal, a spectral representation of the audio signal and a spectral representation of the watermark signal are determined. The spectral representation of the watermark signal is then processed on the basis of a psychoacoustic masking threshold of the audio signal. The processed watermark signal is combined with the audio signal to obtain an audio signal bearing a watermark.

Abstract: A system is provided for allowing a user to add word models to a speech recognition system. In particular, the system allows a user to input a number of renditions of the new word and which generates from these a sequence of phonemes representative of the new word. This representative sequence of phonemes is stored in a word to phoneme dictionary together with the typed version of the word for subsequent use by the speech recognition system.

Abstract: An improved system for an interactive voice recognition system (400) includes a voice prompt generator (401) for generating voice prompt in a first frequency band (501). A speech detector (406) detects presence of speech energy in a second frequency band (502). The first and second frequency bands (501, 502) are essentially conjugate frequency bands. A voice data generator (412) generates voice data based on an output of the voice prompt generator (401) and audible speech of a voice response generator (402). A control signal (422) controls the voice prompt generator (401) based on whether the speech detector (406) detects presence of speech energy in the second frequency band (502). A back end (405) of the interactive voice recognition system (400) is configured to operate on an extracted front end voice feature based on whether the speech detector (406) detects presence of speech energy in the second frequency band (502).

Abstract: An improved method and apparatus is disclosed which uses probabilistic techniques to map an input search string with a prestored audio file, and recognize certain portions of a search string phonetically. An improved interface is disclosed which permits users to input search strings, linguistics, phonetics, or a combination of both, and also allows logic functions to be specified by indicating how far separated specific phonemes are in time.

Abstract: When electric field strength of a reception signal becomes less than a threshold level, an in-vehicle terminal executes one of three operations. The first is that the in-vehicle terminal prohibits input of a voice. The second is that the in-vehicle terminal transmits an inputted voice with a datum indicating radio wave environment to a voice recognition server. The third is that the in-vehicle terminal once stores the inputted voice, and then transmits the inputted voice that has been stored after the electric field strength of the reception signal exceeds the threshold level.

Abstract: A wireless telecommunications system comprises a mobile station (MS) and a network. The mobile station has a multi-rate speech encoder which produces an encoded speech signal which is transmitted to the network. The network has a multi-rate speech decoder which decodes the encoded speech signal to produce a decoded speech signal. The network also comprises a signal analyser which measures speech characteristics of the decoded speech signal to produce speech characteristics information and an up-link mode control unit which receives the speech characteristics information and produces a mode command. The mode command is transmitted by the network to the mobile station where it is used to control the speech encoding bit rate of the multi-rate speech encoder.

Abstract: An improved method and apparatus is disclosed which uses probabilistic techniques to map an input search string with a prestored audio file, and recognize certain portions of a search string phonetically. An improved interface is disclosed which permits users to input search strings, linguistics, phonetics, or a combination of both, and also allows logic functions to be specified by indicating how far separated specific phonemes are in time.

Abstract: Systems and methods for providing synthesized speech in a manner that may take into account the environment where the speech is presented. In certain cases, the manner in which speech is presented can take into consideration ambient noise and/or can seek to optimize speech audibility.

Abstract: One-to-many comparisons of callers'voice prints with known voice prints to identify any matches between them. When a customer communicates with a particular entity, such as a customer service center, the system makes a recording of the real-time call including both the customer's and agent's voices. The system segments the recording to extract at least a portion of the customer's voice to create a customer voice print, and it formats the segmented voice print for network transmission to a server. The server compares the customer's voice print with multiple known voice prints to determine any matches, meaning that the customer's voice print and one of the known voice prints are likely from the same person. The identification of any matches can be used for a variety of purposes, such as determining whether to authorize a transaction requested by the customer.

Abstract: Systems and methods for classifying natural language (NL) sentences using a combination of NL algorithms or techniques is disclosed. Each NL algorithm or technique may identify a different similarity trait between two or more sentences, and each may help compare the meaning of the sentences. By combining the various similarity factors, preferably by various weighting factors, a distance metric can be computed. The distance metric provides a measure of the overall similarity between sentences, and can be used to assign a sentences to an appropriate sentence category.

Abstract: Parsing routines extract from a conventional pronunciation dictionary an entry, which includes a dictionary word and dictionary phonemes representing the pronunciation of the dictionary word. A correspondence table is used to compress the pronunciation dictionary. The correspondence table includes correspondence sets for a particular language, each set having a correspondence text entry, a correspondence phoneme entry representing the pronunciation of the correspondence text entry and a unique correspondence set identifying symbol. A matching system compares a dictionary entry with the correspondence sets, and replaces the dictionary entry with the symbols representing the best matches. In the absence of a match, symbols representing silent text or unmatched phonemes can be used. The correspondence symbols representing the best matches provide compressed pronunciation dictionary entries. The matching system also generates decoder code sets for subsequently translating the symbol sets.