Speech recognition system

Claim 2

A speech recognition system comprising: (a) means for analyzing a speech signal to obtain feature parameters of the speech signal; (b) means for determining start and end points when sound power of the speech signal analyzed by said analyzing means drops below a predetermined threshold, a maximum power and a maximum power point, calculating a means noise level, calculating at least one threshold on the basis of the mean noise level, and searching the sound power from the maximum power point in both rearward and forward directions to obtain word boundary candidates when the sound power drops below the calculated threshold level for a predetermined frame time interval to obtain likelihoods of the obtained start and end word boundary candidates on the basis of frame interval length; (c) means for equally dividing the obtained speech intervals of the obtained word boundary candidates into some sampling points to sample the feature parameters and calculating similiarities between the sampled feature parameters and reference pattern set, at each of the sampling points of the speech interval in the order of the likelihoods from the highest liklihood down to a predetermined lower likelihood; and (d) means for discriminating the speech signal as recognized outputs on the basis of the calculated similiarities obtained at a plurality of determined candidate speech intervals and arranged in the order of the likelihood.

Claim 3

The speech recognition system as set forth in claim 1, wherein said searching means comprises: (a) a first-stage word boundary searcher for determining a start point F O obtained when sound power {P j } analyzed by said analyzing means as one of feature parameters drops below a predetermined threshold P TO into the reverse direction of the time scale for a first predetermined frame time interval F S , an end point B O obtained when the sound power drops below the threshold P TO in the forward direction of the time scale for a second predetermined frame time interval F S , a maximum power P max and a maximum power point F x ; (b) a noise level calculator for calculating a mean front noise level N F near before the start point F O and mean back noise level N B near after the end point N F ; (c) a second-stage word boundary searcher for calculating thresholds P TX on the basis of the mean front noise level N F and the mean back noise level N B , searching the sound power {P j } from the maximum power point F X in the backward direction to obtain start word boundary candidates F 1 , F 2 --when the sound power drops below the threshold level P TX for a predetermined frame time interval F C and to determine the likelihoods of the obtained start word boundary candidates on the basis of the frame time interval length, and searching the sound power {P j } from the maximum power point F X in the forward direction to obtain end word boundary candidates B 1 , B 2 --when the sound power drops below the threshold level P TX for a predetermined frame time interval F C and to determine likelihoods of the obtained end word boundary candidates on the basis of the frame time interval length; and (d) a likelihood calculator for determining likelihoods of speech intervals between the obtained start and end word boundary candidates on the basis of additions of the determined start and end word boundary likelihoods.

Claim 4

The speech recognition system as set forth in claim 2, wherein the threshold P TO is 2 to 5 times higher than background noise level.

Claim 5

The speech recognition system as set forth in claim 2, wherein the means front noise level N F is calculated by averaging noise levels between (F 0 -9) and (F O -1) frames and the mean back noise level N B is calculated by averaging noise levels between (B 0 +1) and (B 0 +9) frames.

Claim 6

The speech recognition system as set forth in claim 2, wherein the threshold P TX is determined as P TX +N F ×(2 to 3).

Claim 7

The speech recognition system as set forth in claim 2, wherein a second threshold P TV is determined as P TV =N F ×(4 to 6), and the likelihood is determined as 1 when sound power {P j } exceeds the threshold P TV for 6 to 8 frames, as 1/4 when {P j } exceeds P TV for 2 to 5 frames, as 0 when {P j } exceeds P TV for 1 to 0 frames, and as 1/2 when a boundary candidate is first searched.

Claim 8

The speech recognition system as set forth in claim 2, wherein a third threshold P V is determined as P max /D, where D is a constant, and a first word boundary candidate F' is cancelled when sound power {P j } exceeds the threshold P V afterward for a predetermined frames.

Claim 11

The method of searching a sound power as set forth in claim 8, wherein the step of determining the start point F 0 and the end point B 0 comprises the following steps of: (a) determining background noise level No; (b) determining a threshold P TO as P TO =3×N 0 ; (c) determining the start point F 0 when the sound power P(J) exceeds the threshold P TO for a predetermined frame time interval F C and the end point B 0 when the sound power P(J) drops below the threshold P TO for a predetermined frame time interval F C after the sound power (PCJ) has reached the maximum power P max .

Claim 12

The method of searching a sound power as set forth in claim 8, wherein the step of determining the mean front and back noise levels N F and N B comprises the following steps of: (a) adding the sound power P(JX) from (F 0 -9) to (F 0 -1) frames; (b) dividing the sound power addition by 9 to obtain the mean front noise level N F ; (c) adding the sound power P(JY) from (B 0 +1) to (B 0 +9) frames; and (d) dividing the sound power addition by 9 to obtain the mean back noise level N B .

Claim 13

The method of searching a sound power as set forth in claim 8, wherein the threshold P TX is determined as P TX =3×N F .

Claim 14

The method of searching a sound power as set forth in claim 8, wherein the step of searching the sound power to determine the likelihoods of the start word boundary candidates comprises: (a) determining the likelihood as 1 when the sound power first drops below the threshold P TX ; (b) determining the likelihood as 0 when the sound power drops below the threshold P TX for 1 or less frame intervals; (c) determining the likelihood as 1/4 when the sound power drops below the threshold P TX for 2 to 5 frame intervals; and (d) determining the likelihood as 1 when the sound power drops below the threshold P TX for 6 or more frame intervals.

Claim 15

The method of searching a sound power as set forth in claim 8, which further comprises the following steps of: (a) determining a second threshold P TV as P TV =2×P TX ; and (b) clearing a counter DCNTR for determining a search end when the sound power lies in level between the first and second thresholds P TX and P TV .

Claim 16

The method of searching a sound power as set forth in claim 8, which further comprises the following steps of: (a) determining a third threshold P V as P V =P max /D where D is constant; (b) clearing a counter DCNTR for determining a search end, a counter ACNTR for determining a likelihood and a likelihood order when the sound power exceeds this third threshold P V for a predetermined frame interval.