Speech Recognition Apparatus Research Articles

Acoustic Model Creation Method as well as Acoustic Model Creation Apparatus and Speech Recognition Apparatus

To provide an acoustic model which can absorb the fluctuation of a phonemic environment in an interval longer than a syllable, with the number of parameters of the acoustic model suppressed to be small, a phoneme-connected syllable HMM/syllable-connected HMM set is generated in such a way that a phoneme-connected syllable HMM set corresponding to individual syllables is generated by combining phoneme HMMs. A preliminary experiment is conducted using the phoneme-connected syllable HMM set and training speech data. Any misrecognized syllable and the preceding syllable of the misrecognized syllable are checked using results of a preliminary experiment syllable label data. The combination between a correct answer syllable for the misrecognized syllable and the preceding syllable of the misrecognized syllable is extracted as a syllable connection. A syllable-connected HMM corresponding to this syllable connection is added into the phoneme-connected syllable HMM set. The resulting phoneme-connected syllable HMM set is trained using the training speech data and the syllable label data.

Method and apparatus for speech recognition

Method and apparatus for speech recognition

Coupled hidden Markov model (CHMM) for continuous audiovisual speech recognition

Method and apparatus for an audiovisual continuous speech recognition (AVCSR) system using a coupled hidden Markov model (CHMM) are described herein. In one aspect, an exemplary process includes receiving an audio data stream and a video data stream, and performing continuous speech recognition based on the audio and video data streams using a plurality of hidden Markov models (HMMs), a node of each of the HMMs at a time slot being subject to one or more nodes of related HMMs at a preceding time slot. Other methods and apparatuses are also described.

Speech recognition apparatus, speech recognition apparatus and program thereof

Provided is a method for canceling background noise of a sound source other than a target direction sound source in order to realize highly accurate speech recognition, and a system using the same. In terms of directional characteristics of a microphone array, due to a capability of approximating a power distribution of each angle of each of possible various sound source directions by use of a sum of coefficient multiples of a base form angle power distribution of a target sound source measured beforehand by base form angle by using a base form sound, and power distribution of a non-directional background sound by base form, only a component of the target sound source direction is extracted at a noise suppression part. In addition, when the target sound source direction is unknown, at a sound source localization part, a distribution for minimizing the approximate residual is selected from base form angle power distributions of various sound source directions to assume a target sound source direction. Further, maximum likelihood estimation is executed by using voice data of the component of the sound source direction passed through these processes, and a voice model obtained by predetermined modeling of the voice data, and speech recognition is carried out based on an obtained assumption value.

Adaptive multi-pass speech recognition system

Method and apparatus for multi-pass speech recognition. An input device receives spoken input. A processor performs a first pass speech recognition technique on the spoken input and forms first pass results. The first pass results include a number of alternative speech expressions, each having an assigned score related to the certainty that the corresponding expression correctly matches the spoken input. The processor selectively performs a second pass speech recognition technique on the spoken input according to the first pass results. Preferably, the second pass attempts to correctly match the spoken input to only those expressions which were identified during the first pass. Otherwise, if one of the expressions identified by the first pass is assigned a score higher than a predetermined threshold (e.g., 95%), the second pass is not performed. Because the second pass is performed only when necessary, the invention recognizes speech with a faster average speed for a given accuracy in comparison to prior systems. Alternately, the first pass results identify a characteristic of the spoken input. The characteristic can be the gender of the speaker or a type of telephone the speaker is calling from. In which case, the second pass speech recognition technique is selected from a plurality of speech recognition techniques according to the characteristic identified by the first pass. Because the selected second pass technique is specific to the characteristic of the spoken input, the second pass technique can perform speech recognition faster for a given accuracy than a technique which is not specific.

Interactive speech recognition apparatus and method with conditioned voice prompts

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).

Ear sensor assembly for speech processing

An ear sensor apparatus includes a microphone positionable with respect to an ear canal (18) to detect sound signals from the ear canal and to generate a corresponding output signal. The apparatus may include a seal (20) for substantially blocking ambient sound signals from reaching the microphone and an interface (24) to convey the output signal to a remote speech recognition apparatus. The output signal may be normalized (42) so that the normalized output signal is more representative of speech from a user's mouth than speech detected from the user's ear.

System and apparatus for speech communication and speech recognition

A headset system is proposed including a headset unit to be worn by a user and having two or more microphones, and a base unit in wireless communication with the headset. Signals received from the microphones are processed using a first adaptive filter to enhance a target signal, and then divided and supplied to a second adaptive filter arranged to reduce interference signals and a third filter arranged to reduce noise. The outputs of the second and third filters are combined, and are be subject to further a processing in the frequency domain. The results are transmitted to a speech recognition engine.

Speech recognition apparatus and method

Speech recognition apparatus and method

Method and apparatus for speech recognition using latent semantic adaptation

A method and apparatus for speech recognition using latent semantic adaptation is described herein. According to one aspect of the present invention, a method for recognizing speech comprises using latent semantic analysis (LSA) to generate an LSA space for a collection of documents and to continually adapt the LSA space with new documents as they become available. Adaptation of the LSA space is optimally two-sided, taking into account the new words in the new documents. Alternatively, adaptation is one-sided, taking into account the new documents but discarding any new words appearing in those documents.

Method and apparatus for selective distributed speech recognition

An apparatus and method for selective distributed speech recognition includes a dialog manager (104) that is capable of receiving a grammar type indicator (170). The dialog manager (104) is capable of being coupled to an external speech recognition engine (108), which may be disposed on a communication network (142). The apparatus and method further includes an audio receiver (102) coupled to the dialog manager (104) wherein the audio receiver (104) receives a speech input (110) and provides an encoded audio input (112) to the dialog manager (104). The method and apparatus also includes an embedded speech recognition engine (106) coupled to the dialog manager (104), such that the dialog manager (104) selects to distribute the encoded audio input (112) to either the embedded speech recognition engine (106) or the external speech recognition engine (108) based on the corresponding grammar type indicator (170).

Method and apparatus for speech recognition using semantic inference and word agglomeration

A method and apparatus for command recognition using semantic inference and word agglomeration is described herein. According to one aspect of the present invention, a method for recognizing a voice command comprises recognizing a sequence of words received as the voice command. The sequence of words is further agglomerated into a sequence of word n-tuples. Semantic inference is applied to the sequence of word n-tuples to recognize the voice command.

Method and apparatus for speech recognition

Method and apparatus for speech recognition

Method and apparatus for speech recognition which is robust to missing speech data

A speech recognizer suitable for distributed speech recognition is robust to missing speech feature vectors. Speech is transmitted via a packet switched network in the form of basic feature vectors. Missing feature vectors are detected and replacement feature vectors are estimated by interpolation of received data prior to speech recognition. Features may be converted and interpolation may be accomplished in a spectral domain.

Speech recognition apparatus using distance based acoustic models

The present invention relates to a speech recognition apparatus and a speech recognition method for speech recognition with improved accuracy. A distance calculator 47 determines the distance from a microphone 21 to a user uttering. Data indicating the determined distance is supplied to a speech recognition unit 41 B. The speech recognition unit 41 B has plural sets of acoustic models produced from speech data obtained by capturing speeches uttered at various distances. From those sets of acoustic models, the speech recognition unit 41 B selects a set of acoustic models produced from speech data uttered at a distance closest to the distance determined by the distance calculator 47, and the speech recognition unit 41 B performs speech recognition using the selected set of acoustic models.

Speech recognition apparatus having multiple audio inputs to cancel background noise from input speech

A speech recognition apparatus including an audio cancellation module is disclosed. The module includes an audio input for receiving an audio signal from a microphone. The module also includes at least two audio inputs for receiving audio signals from respective independent audio sources. The audio cancellation module produces a speech signal by canceling two of the independent audio source signals from the microphone signal. A speech recognizer is used to recognize at least part of the speech signal.

Apparatus and method for speech recognition

An apparatus and a method for speech recognition are provided, by which, whereby the speech is optionally input via a microphone ( 14 ) close to the speaker or a microphone ( 20 ) remote from the speaker. A correction unit ( 15 ) is connected into the transmission channel ( 12 ) with microphone ( 14 ) close to the speaker, the correction unit modifying the electrical speech signal in such a way that it contains room transmission characteristics.

Speech processing apparatus and method employing matching and confidence scores

A speech recognition method and apparatus is disclosed in which each utterance matched to a feature model within a feature model memory ( 110 ) is associated with a confidence score indicative of the posterior probability of the word being correctly matched, given that the matching of the utterance to the feature model generated certain values indicative of the goodness of the match. The confidence score for the matching of an utterance to a feature model is determined from the generated values indicative of the goodness of the match and a stored set of parameters indicating the probability of the generated values arising given that a match is either correct or incorrect.

Speech processing apparatus and method using confidence scores

A speech recognition method and apparatus is disclosed in which outputs a confidence score indicative of the posterior probability of an utterance being correctly matched to a word model. The confidence score for the matching of an utterance to a word model is determined directly from the generated values indicative of the goodness of match between the utterance and stored word models utilizing the following equation: confidence = exp ⁡ ( - 2 σ ⁢ S ⁡ ( x | w ) ) ∑ words ⁢ exp ⁡ ( 2 σ ⁢ S ⁡ ( x | w ) ) where S(x|w) is the match score for the correlation between a signal x and word w and σ is an experimentally determined constant.

Environment adaptation for speech recognition in a speech communication system

A speech communication system comprising a speech input terminal and a speech recognition apparatus which can communicate with each other through a wire or wireless communication network wherein the speech input terminal comprises speech input unit, a unit for creating environment information for speech recognition, which is unique to the speech input terminal or represents its operation state, and a communication control unit for transmitting the environment information to the speech recognition apparatus, and the speech recognition apparatus executes speech recognition processing on the basis of the environment information.