Abstract: Tone-sensitive acoustic models are generated by first generating acoustic vectors which represent the input data. The input data is separated into multiple frames and an acoustic vector is generated for each frame which represents the input data over its corresponding frame. A tone-sensitive parameter is then generated for each of the frames which indicates the tone of the input data at its corresponding frame. Tone-sensitive parameters are generated in accordance with two embodiments. First, a pitch detector may be used to calculate a pitch for each of the frames. If a pitch cannot be detected for a particular frame, then a pitch is created for that frame based on the pitch values of surrounding frames. Second, the cross covariance between the autocorrelation coefficients for each frame and its successive frame may be generated and used as the tone-sensitive parameter.

Abstract: A method for reducing recognition errors in a speech recognition system that has a user interface, which instructs the user to invoke a new word acquisition module upon a predetermined condition, and that improves the recognition accuracy for poorly recognized words. The user interface of the present invention suggests to a user which unrecognized words may be new words that should be added to the recognition program lexicon. The user interface advises the user to enter words into a new word lexicon that fails to present themselves in an alternative word list for two consecutive tries. A method to improve the recognition accuracy for poorly recognized words via language model adaptation is also provided by the present invention. The present invention increases the unigram probability of an unrecognized word in proportion to the score difference between the unrecognized word and the top one word to guarantee recognition of the same word in a subsequent try.

Abstract: A method of constructing a language model for a phrase-based search in a speech recognition system and an apparatus for constructing and/or searching through the language model. The method includes the step of separating a plurality of phrases into a plurality of words in a prefix word, body word, and suffix word structure. Each of the phrases has a body word and optionally a prefix word and a suffix word. The words are grouped into a plurality of prefix word classes, a plurality of body word classes, and a plurality of suffix word classes in accordance with a set of predetermined linguistic rules. Each of the respective prefix, body, and suffix word classes includes a number of prefix words of same category, a number of body words of same category, and a number of suffix words of same category, respectively. The prefix, body, and suffix word classes are then interconnected together according to the predetermined linguistic rules.

Abstract: A method and system for editing words that have been misrecognized. The system allows a speaker to specify a number of alternative words to be displayed in a correction window by resizing the correction window. The system also displays the words in the correction window in alphabetical order. A preferred system eliminates the possibility, when a misrecognized word is respoken, that the respoken utterance will be again recognized as the same misrecognized word. This elimination occurs based on the probabilities of alternative words associated with both the misrecognized utterance and the respoken utterance. The system, when operating with a word processor, allows the speaker to specify the amount of speech that is buffered before transferring to the word processor. The system also uses a word correction metaphor or a phrase correction metaphor.

Abstract: A method of correcting a text in a data processing system is described. The method includes the step of locating a first incorrect character in the text. A character list of alternative characters for the first incorrect character is then shown to the user who replaces the first incorrect character with a correct character from the character list. The change of the first incorrect character is then propagated through a remainder of the text in accordance with a matching score and a language probability score of the remainder of the text with respect to the correct character to correct any subsequent incorrect character in the text.

Abstract: A speech recognition system for Mandarin Chinese comprises a preprocessor, HMM storage, speech identifier, and speech determinator. The speech identifier includes pseudo initials for representing glottal stops that precede syllables of lone finals. The HMM storage stores context dependent models of the initials, finals, and pseudo initials that make the syllables of Mandarin Chinese speech. The models may be dependent on associated initials or finals and on the tone of the syllable. The speech determinator joins the initials and finals and pseudo initials and finals according to the syllables of the speech identifier. The speech determinator then compares input signals of syllables to the joined models to determine the phonetic structure of the syllable and the tone of the syllable. The system also includes a smoother for smoothing models to make recognitions more robust. The smoother comprises an LDM generator and a detailed model modifier.

Abstract: A pattern recognition system which continuously adapts reference patterns to more effectively recognize input data from a given source. The input data is converted to a set or series of observed vectors and is compared to a set of Markov Models. The closest matching Model is determined and is recognized as being the input data. Reference vectors which are associated with the selected Model are compared to the observed vectors and updated ("adapted") to better represent or match the observed vectors. This updating method retains the value of these observed vectors in a set of accumulation vectors in order to base future adaptations on a broader data set. When updating, the system also may factor in the values corresponding to neighboring reference vectors that are acoustically similar if the data set from the single reference vector is insufficient for an accurate calculation.

Abstract: A speech recognition system for continuous Mandarin Chinese speech comprises a microphone, an A/D converter, a syllable recognition system, an integrated tone classifier, and a confidence score augmentor. The syllable recognition system generates N-best theories with initial confidence scores. The integrated tone classifier has a pitch estimator to estimate the pitch of the input once and a long-term tone analyzer to segment the estimated pitch according to the syllables of each of the N-best theories. The long-term tone analyzer performs long-term tonal analysis on the segmented, estimated pitch and generates a long-term tonal confidence signal. The confidence score augmentor receives the initial confidence scores and the long-term tonal confidence signals, modifies each initial confidence score according to the corresponding long-term tonal confidence signal, re-ranks the N-best theories according to the augmented confidence scores, and outputs the N-best theories.