Abstract: Talking toys perform simulated conversations with one another. The toys each include a forest of decision graphs. The forest of decision graphs is the same for each toy. Each of the decision graphs corresponds to a conversation and includes a number of nodes, each of which corresponds to a portion of the conversation. The nodes also include one or more contexts which connect the nodes to children nodes. As a result, the selection of the context directs the progression of conversation. The toys select a decision graph/conversation that includes all or most of the toys as participants. The conversation is then performed as the toys traverse the selected decision graph. The toys transfer messages back and forth via a wireless transmission and reception arrangement as they traverse the decision graph. The toys play the portions of the conversation through a speaker.

Abstract: An intelligent query system for processing voiced-based queries is disclosed. This distributed client-server system, typically implemented on an intranet or over the Internet accepts a user's queries at his/her computer, PDA or workstation using a speech input interface. After converting the user's query from speech to text, a 2-step algorithm employing a natural language engine, a database processor and a full-text SQL database is implemented to find a single answer that best matches the user's query. The system, as implemented, accepts environmental variables selected by the user and is scalable to provide answers to a variety and quantity of user-initiated queries.

Abstract: A system for real time transmission of speech audio received from a text-to-speech (TTS) engine can include a TTS engine and a real time speech audio producer for receiving speech audio from the TTS engine over a network, and for producing formatted audio packets for transmission over the network according to the transmission interval. The transmission interval can be determined according to a packetization delay parameter.

Abstract: An automatic speech recognition system for the condition that an incoming caller's speech is quiet and a resulting echo (of a loud playing prompt) can cause the residual (the portion of the echo remaining after even echo cancellation) to be of the magnitude of the incoming speech input. Such loud echoes can falsely trigger the speech recognition system and interfere with the recognition of valid input speech. An echo model has been proven to alleviate this fairly common problem and to be effective in eliminating such false triggering. Further, this automatic speech recognition system enhanced the recognition of valid speech was provided within an existing hidden Markov modeling framework.

Abstract: A system and method for the creation and automatic deployment of personalized, dynamic and interactive voice services, including information derived from on-line analytical processing (OLAP) systems and other data repositories is disclosed. In particular, the system and method include the ability to deploy voice services through a digital sound file. The system and method access personalized information and generate personalized markup documents from the personalized information. The personalized markup document is used to generate a sound file that is made available to a subscriber of the voice service, for example, through an e-mail or by posting to a web site.

Abstract: A speech recognition method is disclosed for activating a hyperlink of an Internet page. In particular the method comprises determining hypertexts of the hyperlinks in text information, determining corresponding first phoneme sequences of hypertexts, receiving a spoken command from a user, determining a second phoneme sequence corresponding to the spoken command, determining the hyperlink selected by the user using the first and second phoneme sequences, activating the selected hyperlink, where one quality value is determined for each hypertext when first phoneme sequences are determined and where an extra hypertext is determined when the quality value of a hypertext is below a threshold and is assigned to the hypertext of the Internet page or in lieu of the hypertext, and where a first phoneme sequence determined for the extra hypertext has a quality value that exceeds the threshold.

Abstract: Disclosed is a voice recognition apparatus which can prevent an erroneous manipulation due to erroneous voice recognition from being carried out even in a noisy environment. As long as a duration of utterance acquired based on the level of a voice signal uttered by an operator (user) approximately coincides with a duration of utterance acquired based on mouth image data acquired by capturing the mouth of the operator, the voice recognition apparatus outputs vocal-manipulation phrase data as the result of voice recognition.

Abstract: A speech compression system capable of encoding a speech signal into a bitstream for subsequent decoding to generate synthesized speech is disclosed. The speech compression system optimizes the bandwidth consumed by the bitstream by balancing the desired average bit rate with the perceptual quality of the reconstructed speech. The speech compression system comprises a full-rate codec, a half-rate codec, a quarter-rate codec and an eighth-rate codec. The codecs are selectively activated based on a rate selection. In addition, the full and half-rate codecs are selectively activated based on a type classification. Each codec is selectively activated to encode and decode the speech signals at different bit rates emphasizing different aspects of the speech signal to enhance overall quality of the synthesized speech.

Abstract: To improve the precision in correction of an input sentence by using a template pattern for model sentence. A plurality of template patterns for the model sentence are provided beforehand. Each of the template patterns is regarded as a plurality of templates of words/phrases based on expertise of language teachers with scores assigned to the words according to their importance. The scores and subsequently the input sentence are read and analyzed in comparison with each of the template patterns and the total of scores of matching words is calculated. A template pattern having the highest total score is selected as an optimum template pattern and the input sentence is corrected using the optimum template pattern. This method improves the likelihood that a template pattern containing a larger number of important words is selected as the optimum template pattern.

Abstract: An apparatus for voice-activated control of an electrical device comprises a receiving arrangement for receiving audio data generated by user. A vioce recognition arrangement is provided for determining whether the received audio data is a command word for controlling the electrical device. The voice recognition arrangement includes a microprocessor for comparing the received audio data with voice recognition data previously stored in the voice recognition arrangement. The voice recognition arrangment generates at least one control signal based on the comparison when the comparison reaches a predetermined threshold value. A power control controls power delivered to the electrical device. The power control is responsive to at least one control signal generated by the voice recognition arrangement for operating the electrical device in response to the at least one audio command generated by the user.

Abstract: A method and apparatus for coding successive pitch periods of a speech signal. Based on a priori knowledge of statistical properties of successive speech periods, a shaped lattice structure is designed to cover the most probable points in the pitch space. The codebook index search starts with finding an open-loop estimate in the pitch space considering all dimensions and refining the open-loop estimate in a closed-loop search separately in each dimension based on the shaped lattice structure. The closed-loop search for the first subframe is for obtaining an absolute pitch period or a delta pitch while the closed-loop search for each of the other subframes is for obtaining a delta pitch for the respective subframe.

Abstract: A speech compression system capable of encoding a speech signal into a bitstream for subsequent decoding to generate synthesized speech is disclosed. The speech compression system optimizes the bandwidth consumed by the bitstream by balancing the desired average bit rate with the perceptual quality of the reconstructed speech. The speech compression system comprises a full-rate codec, a half-rate codec, a quarter-rate codec and an eighth-rate codec. The codecs are selectively activated based on a rate selection. In addition, the full and half-rate codecs are selectively activated based on a type classification. Each codec is selectively activated to encode and decode the speech signals at different bit rates emphasizing different aspects of the speech signal to enhance overall quality of the synthesized speech.

Abstract: A unified web-based voice messaging system provides voice application control between a web browser and an application server via an hypertext transport protocol (HTTP) connection on an Internet Protocol (IP) network. The application server executes the voice-enabled web application by runtime execution of a first set of extensible markup language (XML) documents that define the voice-enabled web application to be executed. The application server generates an HTML form specifying selected application parameters from an XML document executable by the voice application. The HTML form is supplied to a browser, enabling a user of the browser to input or modify application parameters for the corresponding XML document into the form. The application server inserts the received input application parameters into the XML document, and stores the document.

Abstract: A speech compression system capable of encoding a speech signal into a bitstream for subsequent decoding to generate synthesized speech is disclosed. The speech compression system optimizes the bandwidth consumed by the bitstream by balancing the desired average bit rate with the perceptual quality of the reconstructed speech. The speech compression system comprises a full-rate codec, a half-rate codec, a quarter-rate codec and an eighth-rate codec. The codecs are selectively activated based on a rate selection. In addition, the full and half-rate codecs are selectively activated based on a type classification. Each codec is selectively activated to encode and decode the speech signals at different bit rates emphasizing different aspects of the speech signal to enhance overall quality of the synthesized speech.

Abstract: A reduced dimensionality eigenvoice analytical technique is used during training to develop context-dependent acoustic models for allophones. The eigenvoice technique is also used during run time upon the speech of a new speaker. The technique removes individual speaker idiosyncrasies, to produce more universally applicable and robust allophone models. In one embodiment the eigenvoice technique is used to identify the centroid of each speaker, which may then be “subtracted out” of the recognition equation. In another embodiment maximum likelihood estimation techniques are used to develop common decision tree frameworks that may be shared across all speakers when constructing the eigenvoice representation of speaker space.

Abstract: An expansion processor has a buffer defining unit for defining one of two buffers as a present inverse quantization buffer and defining one of two buffers as a present restoration buffer, an inverse quantization processor for inversely quantizing a quantized value read for each sample from a DCT data buffer, an IDCT processor for effecting an IDCT process on the inversely quantized data to restore time-domain audio data from frequency-domain data, a low-pass filter processor for removing a high-frequency component from the restored audio data, and an audio data output unit for outputting successive restored samples of audio data to a DAC to output sound from a speaker.

Abstract: A digital filter design apparatus for noise suppression by spectral subtraction includes a first spectrum estimator for determining a high frequency resolution noisy speech power spectral density estimate from a noisy speech signal block. A second spectrum estimator determines a high frequency resolution background noise power spectral density estimate from a background noise signal block. Averaging units form a piece-wise constant noisy speech power spectral density estimate and a piece-wise constant background noise power spectral density estimate. These averaging units are controlled by devices for adapting the length of individual segments to the shape of the high frequency-resolution noisy speech power spectral density estimate and for using the same segmentation in both piecewise constant estimates.

Abstract: A speech compression system with a special fixed codebook structure and a new search routine is proposed for speech coding. The system is capable of encoding a speech signal into a bitstream for subsequent decoding to generate synthesized speech. The codebook structure uses a plurality of subcodebooks. Each subcodebook is designed to fit a specific group of speech signals. A criterion value is calculated for each subcodebook to minimize an error signal in a minimization loop as part of the coding system. An external signal sets a maximum bitstream rate for delivering encoded speech into a communications system. The speech compression system comprises a full-rate codec, a half-rate codec, a quarter-rate codec and an eighth-rate codec. Each codec is selectively activated to encode and decode the speech signals at different bit rates to enhance overall quality of the synthesized speech at a limited average bit rate.

Abstract: A low complexity speaker verification system that employs universal cohort models an automatic score thresholding. The universal cohort models are generated using a simplified cohort model generating scheme. In certain embodiments of the invention, a simplified hidden Markov modeling (HMM) scheme is used to generate the cohort models. In addition, the low complexity speaker verification system is trained by various users of the low complexity speaker verification system. The total number of users of the low complexity speaker verification system may be modified over time as required by the specific application, and the universal cohort models may be updated accordingly to accommodate the new users. The present invention employs a combination of universal cohort modeling and thresholding to ensure high performance.

Abstract: The invention relates to a method and apparatus for generating transcriptions suitable for use in a speech-processing device. The invention provides processing the vocabulary item to derive a characteristic from the vocabulary item allowing to divide a pool of available languages in a first sub-group and a second sub-group. The vocabulary item manifests a higher probability of belonging to any one of the languages in the first sub-group than belonging to any language in the second sub-group. The invention further provides processing the vocabulary item to generate a group of transcriptions, the group of transcriptions being characterized by the absence of at least one transcription belonging to a language in the second sub-group of languages established for the vocabulary item. The group of transcriptions is then released for use by a speech-processing device.