Speech recognition

Claim 2

Aspeech recognition processing unit, comprising storage means for storing label information for a set of labels indicative of phone types each assignable to a predetermined time period; logic for converting input speech into a label stream on the basis of the stored label information; logic for accumulating probabilities based on the label stream and word models for words in a vocabulary defined by Markov model probability information for words in a vocabulary; logic for determining one or more words to be the result of the recognition on the basis of the accumulated probabilities; characterised in that the unit is for use with, and connectable to the bus of, a computer, which computer includes a main memory in which the Markov model probability information defining the word models is stored, the unit comprising means for fetching the stored Markov model probability information related to the labels in the label stream as required by direct memory access transfer from the main memory of the computer.

Claim 3

A speech recognition processing unit as claimed in claim 1, wherein the means for fetching the probability values by direct memory access transfer is a bus master.

Claim 4

A speech recognition processing unit as claimed in claim 1 or claim 2, including a memory device having a speed higherthan that of the main memory, said memory device temporarily storing said fetched probability values and storing the accumulated probability values.

Claim 5

A speech recognition system comprising a processing unit as claimed in any preceding claim and a computer, which computer includes a main memory.

Claim 6

A speech recognition system for storing information on probability values of Markov models defining speech models of vocabulary words and information on a set of labels indicating phone types assignable to a micro period of time, for sequentially generating corresponding labels in response to an input speech to generate a label stream of said input speech, for accumulating said probability values of said Markov models on the basis of said speech models of said words and said label stream, and for performing speech recognition on the basis of the accumulated values, comprising: a bus; a processor coupled to said bus; a main memory for said processor for storing said probability values of said Markov models accessively to each of said labels, said main memory being coupled to said bus; and a signal processing unit coupled to said bus, said signal processing unit icomprising: means for storing information on said set of labels; means for converting an input speech into said label stream on the basis of said information on the set of labels; means for fetching said probability values of a Markov model related to each of labels contained in said label stream by direct memory access transfer from said main memory; means for accumulating said probability values thus fetched for each of said vocabulary words; and means for determining one or more words to be the result of the recognition on the basis of accumulated probability values.

Claim 7

A speech recognition system for storing information on probability values of Markov models defining speech models of vocabulary words and information on a set of labels indicating phone types assignable to a micro period of time, for sequentially generating corresponding labels in response to an input speech to generate a label stream of said input speech, for accumulating said probability values of said Markov models on the basis of said speech models of said words and said label stream, and for performing speech recognition on the basis of the accumulated values, comprising: a bus; a processor coupled to said bus; a main memory for said processor for storing said probability values of said Markov models accessively to each of said labels, said main memory being coupled to said bus; and a signal processing unit coupled to said bus, said signal processing unit icomprising: means for storing information on said set of labels; means for converting an input speech into said label stream on the basis of said information on the set of labels; means for fetching said probability values of a Markov model related to each of labels contained in said label stream by direct memory access transfer from said main memory; means for accumulating said probability values thus fetched for each of said vocabulary words; and means for determining one or more words to be the result of the recognition on the basis of accumulated probability values.

Claim 8

A speech recognition system as claimed in claim 5, wherein said means for fetching said probability values by direct memory access transfer is a bus master.

Claim 9

A speech recognition system as claimed in claim 6, wherein said signal processing unit includes a memory having a speed higher than that of said main memory, said memory temporarily storing said fetched probability values and storing said accumulated probability values.

Claim 10

A speech recognition processing unit connectable to a bus of a computer system which computer system includes a processor, a main memory, and an input and output devices coupled in common to said bus, said unit comprising: means for converting an input speech into a label stream on the basis of information on a set of labels indicating phone types assignable to a micro period of time; means for fetching probability values of a Markov model related to each label contained in said label stream by direct memory access transfer from a main memory which beforehand stores information on said probability values of said Markov models defining speech models of vocabulary words, said information being arranged accessively to each of said labels; means responsive to probability values thus fetched for accumulating said probability values for each of said words; and means responsive to the accumulated probability values for determining one or more words to be the result of the recognition.

Claim 11

A speech recognition processing unit connectable to a bus of a computer system which computer system includes a processor, a main memory, and an input and output devices coupled in common to said bus, said unit comprising: means for converting an input speech into a label stream on the basis of information on a set of labels indicating phone types assignable to a micro period of time; means for fetching probability values of a Markov model related to each label contained in said label stream by direct memory access transfer from a main memory which beforehand stores information on said probability values of said Markov models defining speech models of vocabulary words, said information being arranged accessively to each of said labels; means responsive to probability values thus fetched for accumulating said probability values for each of said words; and means responsive to the accumulated probability values for determining one or more words to be the result of the recognition.

Claim 12

A speech recognition system for storing information on a set of first labels indicating phone types assignable to a micro period of time, information on probabilities that respective ones of said first labels are produced in utterance of respective vocabulary words, information on speech models of said vocabulary words each represented as a chain of Markov models in a set which set includes Markov models corresponding to respective second labels indicating phone types assignable to a micro period of time, and information on probability values of said Markov models, in response to an input speech, for sequentially producing corresponding first labels to generate a first label stream of said input speech, for determining whether said vacabulary words are recognition candidates by using said first label streams and said probabilities that respective ones of said first labels are produced in utterance of respective vocabulary words, for accumulating said probability values of said Markov models on the basis of speech models of said recognition candidates and said first label stream, and for performing detailed speech recognition on the basis of accumulated probability values, comprising: a bus; a processor coupled to said bus; a main memory for said processor for storing information of said probabilities thatrespec- tive ones of said first labels are produced in utterance of respective ones of said vacabulary words, accesssively to each of said first labels, and storing information on speech models of said words accessively to each of said vacabulary words, said main memory being coupled to said bus; and a signal processing unit coupled to said bus, further said signal processing unit including: means for converting said input speech into said first label stream; means for fetching, for each of labels contained in said first label stream, information on probabilities that respective ones of said vacabulary words produce said first label, said information being fetched by direct memory access transfer from said main memory; means for accumulating probabilities thus fetched for said vocabulary word respectively upon each of said labels contained in said first label stream; means for determining candidate words on the basis of the accumulated probabilities; means, for each of first labels contained in said first label stream, forfetching information on values of probability that respective ones of said labels are produced in each transition, said information being fetched by direct memory access transfer from said main memory; means for computing likelihood that said word candidates be said input speech in response to said information on speech models and said information on probability values fetched for respective ones of said first labels; and means for generating a recognition result on the basis of said likelihood.

Claim 13

A speech recognition system for storing information on a set of first labels indicating phone types assignable to a micro period of time, information on probabilities that respective ones of said first labels are produced in utterance of respective vocabulary words, information on speech models of said vocabulary words each represented as a chain of Markov models in a set which set includes Markov models corresponding to respective second labels indicating phone types assignable to a micro period of time, and information on probability values of said Markov models, in response to an input speech, for sequentially producing corresponding first labels to generate a first label stream of said input speech, for determining whether said vacabulary words are recognition candidates by using said first label streams and said probabilities that respective ones of said first labels are produced in utterance of respective vocabulary words, for accumulating said probability values of said Markov models on the basis of speech models of said recognition candidates and said first label stream, and for performing detailed speech recognition on the basis of accumulated probability values, comprising: a bus; a processor coupled to said bus; a main memory for said processor for storing information of said probabilities thatrespec- tive ones of said first labels are produced in utterance of respective ones of said vacabulary words, accesssively to each of said first labels, and storing information on speech models of said words accessively to each of said vacabulary words, said main memory being coupled to said bus; and a signal processing unit coupled to said bus, further said signal processing unit including: means for converting said input speech into said first label stream; means for fetching, for each of labels contained in said first label stream, information on probabilities that respective ones of said vacabulary words produce said first label, said information being fetched by direct memory access transfer from said main memory; means for accumulating probabilities thus fetched for said vocabulary word respectively upon each of said labels contained in said first label stream; means for determining candidate words on the basis of the accumulated probabilities; means, for each of first labels contained in said first label stream, forfetching information on values of probability that respective ones of said labels are produced in each transition, said information being fetched by direct memory access transfer from said main memory; means for computing likelihood that said word candidates be said input speech in response to said information on speech models and said information on probability values fetched for respective ones of said first labels; and means for generating a recognition result on the basis of said likelihood.