Speech recognition system

• US 4,876,720 A
• Filed: 03/12/1987
• Issued: 10/24/1989
• Est. Priority Date: 03/25/1986
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kaneko, Toyohisa, Watanuki, Osaaki
• Primary Examiner(s): Roskoski, Bernard
• Application Number:
  US07/025,126
• Time in Patent Office: 957 Days
• Field of Search: 381/41-43, 381/45, 381/51, 364/513.5
• US Class Current: 704/240
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence

Abstract

The invention relates to a muffler which includes a first expansion chamber, a second expansion chamber, a resonator chamber, and an inlet pipe having a first open end and a second open end. The first open end of the inlet pipe is inserted into the first expansion chamber so as to communicate with the latter. A resonator pipe runs substantially in a coaxial relationship with the inlet pipe so as to establish communication between the first expansion chamber and the resonant chamber. A return pipe is disposed between the resonator chamber and the second expansion chamber and passes through the first expansion chamber for establishing communication between the first expansion chamber and the second expansion chamber. An outlet pipe communicates with the second expansion chamber. The improvement comprises that said return pipe has an open end and is inserted with the open end into said resonator chamber, while the inserted open end thereof is sealed with a plug. A portion of the return pipe, passing through the first expansion chamber and the resonator chamber, is provided with at least a throughhole.

Claims

1. A speech recognition system comprising:

means for storing probabilities of each of a plurality of labels being produced in each of a plurality of first segments in each of a plurality of recognition units;

means for generating a label string from an input unit;

means for segmenting said label string into a plurality of second segments, each corresponding to each of said first segments;

means for calculating, for each recognition unit, a likelihood that said input unit represents the recognition unit, by reading out from said storing means, for each of said labels in said label string, said probabilities of each of said labels associated with said one recognition unit and corresponding to each of said labels in said label string, according to the identity of each of said labels in said label string and the identity of each of said second segments to which each of said labels in said label string belongs;

means for determining a recognition unit having the highest likelihood among said recognition units, as a recognition result, according to the outputs of said likelihood calculating means.

2. A speech system as described in claim 1 further comprising:

means for preselecting candidates for said recognition result according to the length of said input unit.

3. A speech recognition system as described in claim 1 wherein:

said likelihood calculating means obtains said likelihood by calculating the sum of the logarithms of said probabilities read out associated with said one recognition unit.

4. A speech recognition method comprising the steps of:

(a) where each word Wj in a vocabulary is partitioned into a sequence of segments S1(Wj), S2(Wj),...,Sn(Wj), storing probabilities for each label of an alphabet of labels being produced at each segment of each vocabulary word;

(b) generating a string of labels in response to an uttered speech input, each label in the string being selected from the label alphabet, said selection being based on predefined speech characteristics;

(c) segmenting the generated string of labels into a sequence of segments s1,s2,...,sn aligned with the respective segments S1(Wj),S2(Wj),...,Sn(Wj) for each of the vocabulary words Wj;

(d) calculating the likelihood of each vocabulary word producing the string of labels for the uttered input including the steps of;

(i) reading out the respective probabilities for each label in the segment s1 which is stored for the segment S1(W1) for a word W1;

(ii) repeating the step (i) for each label in each segment s2 through sn, one segment after another, in order to read out probabilities stored for corresponding segments S2(W1), S3(W1),...,Sn(W1);

(iii) repeating steps (d) (i) and (d) (ii) for each word Wj; and

(e) determining, based on the probabilities read out in step (d), which vocabulary word has the highest likelihood of having produced the generated string of labels for the input.

5. The method of claim 4 comprising the further steps of:

(f) training the probabilities stored in step (a) including the steps of;

(i) generating at least one string of labels in response to at least one corresponding utterance of a known subject vocabulary word;

(ii) for each generated string for the known word, normalizing the string to a length of N_f labels;

(iii) partitioning each normalized string of N_f labels into N_b segments S1(Wj), S2(Wj),..., Sn(Wj) each segment having the same number N_f /N_b of labels;

(iv) determining counts, based on the label strings generated in response to the utterance of the known word, indicating how often each label occurred in each segment S1(Wj) through Sn(Wj); and

(v) repeating steps (f) (i) through (f) (iv) for each vocabulary word.

6. The method of claim 5 comprising the further step of:

(g) normalizing the string of labels generated in response to an speech input to include N_f labels which may be segmented into N_b segments sl through sn.

7. A speech recognition method comprising the steps of:

providing a vocabulary of at least two words W₁ and W₂ ;

partitioning word W₁ into a sequence of at least two segments S₁ (W₁) and S₂ (W₁);

partitioning word W₂ into a sequence of at least two segments S₁ (W₂) and S₂ W₂);

providing an alphabet of labels f_i ;

generating probabilities P(f_i |S₁ (W₁)) of occurrence of each label f_i given the occurrence of the segment S₁ (W₁);

generating probabilities P(f_i`l |S₂ (W₁)) of occurrence of each label f_i given the occurrence of the segment S₁ (W₁);

generating probabilities P(f_i |S₂ (W₂)) of occurrence of each label f_i given the occurrence of the segment S₂ (W₁);

generating probabilities P(f_i |S₂ (W₂)) of occurrence of each label f_i `given the occurrence of the segment S₁ (W₂);

generating a sequence of labels L_i (W₃), L₂ (W₃), ..., L_m (W₃) representing an input speech W₃ to be recognized;

partitioning the sequence of labels representing input speech W₃ into a sequence of at least two segments S₁ (W₃) and S₂ (W₃) to produce a sequence of labels L_i (S₁ (W₃)), L₂ (S₁ (W₃)), ..., L_q (S₁ (W₃)), L_q+1 (S₂ (W₃)), L_q+2 (S₂ (W₃)), ..., L_m (S₂ (W₃));

calculating the likelihood of occurrence of word W₁ given the sequence of labels representing the input speech W₃, based on the probabilities P(L₁ (S_k (W₃))|S_k (W₁)) of occurrence of the labels representing word W₃ given the occurrence of segment S_k of word W₁ ;

calculating the likelihood of occurrence of word W₂ given the sequence of labels representing the input speech W₃, based on the probabilities P(L_i (S_k (W₃))|S_k (W₂)) of occurrence of the labels representing word W₃ given the occurrence of segment S_k of word W₂ ;

generating an output signal identifying the input speech W₃ as the word W₁ or W₂ with the higher calculated likelihood of occurrence.

8. A method as claimed in claim 7, characterized in that:

the step of calcalating the likelihood of occurrence of word W₁ comprises the step of calculating the sum of the logarithms of the probabilities P(L₁ (S_k (W₃))|S_k (W₁)) of occurrence of the labels representing word W₃ given the occurrence of segment S_k of word W₁ ; and

the step of calculating the likelihood of occurrence of word W₂ comprises the step of calculating the sum of the logarithms of the probabilities P(L_i (S_k (W₃))|S_k (W₂)) of occurrence of the labels representing word W₃ given the occurrence of segment S_k of word W₂.

9. A method as claimed in claim 7, further comprising the steps of:

generating maximum and minimum speech length information for word w₁ ;

generating maximum and minimum speech length information for word W₂ ;

determining the length of word W₃ ;

setting the likelihood of occurrence of word W₁ substantially equal to zero if the length of word W₃ is (i) greater than the maximum speech length information for word W₁, or (ii) less than the minimum speech length information for word W₁ ; and

setting the likelihood of occurrence of word W₂ substantially equal to zero if the length of word W₃ is (i) greater than the maximum speech length information for word W₂ or (ii) less than the minimum speech length information for word W₂.

10. A speech recognition system having a vocabulary of at least two words W₁ and W₂, and having an alphabet of labels f_i, word W₁ being partitioned into a sequence of at least two segments S₁ (W₁)kl and S₂ (W₁), word W₂ being partitioned into a sequence of at least two segments S₁ (W₂) and S₂ (W₂), said system comprising:

means for generating probabilities P(f_i |S₁ (W₁)) of occurrence of each label f_i given the occurrence of the segment S₁ (W₁);

means for generating probabilities P(f_i |S₂ (W₁)) of occurrence of each label f_i given the occurrence of the segment S₂ (W₁);

means for generating probabilities P(f_i |S₁ (W₂)) of occurrence of each label f_i given the occurrence of the segment S₁ (W₂);

means for generating probabilities P(f_i |S₂ (W₂)) of occurrence of each label f_i given the occurrence of the segment S₂ (W₂);

means for generating a sequence of labels L₁ (W₃), L₂ (W₃), ..., L_m (W₃) representing an input speech W₃ to be recognized;

means for partitioning the sequence of labels representing input speech W₃ into a sequence of at least two segments S₁ (W₃) and S₂ (W₃) to produce a sequence of labels L₁ (S₁ (W₃)), L₂ (S₁ (W₃)), ..., L_q (S₁ (W₃)), L_q+1 (S₂ (W₃)), L_q2 (S₂ (W₃)), ..., L_m (S₂ (W₃));

means for calculating the likelihood of occurrence of word W₁ given the sequence of labels representing the input speech W₃, based on the probabilities P(L_i (S_k (W₃))|S_k (W₁)) of occurrence of the labels representing word W₃ given the occurrence of segment S_k of word W₁ ;

means for calculating the likelihood of occurrence of word W₂ given the sequence of labels representing the input speech W₃, based on the probabilities P(L_i (S_k (W₃))|S_k (W₂)) of occurrence of the labels representing word W₃ given the occurrence of segment S_k of word W₂ ;

means for generating an output signal identifying the input speech W₃ as the word W₁ or W₂ with the higher calculated likelihood of occurrence.

11. A system as claimed in claim 10, characterized in that:

the means for calculating the likelihood of occurrence of word W₁ comprises means for calculating the sum of the logarithms of the probabilities P(L_i (S_k (W₃))|S_k (W₁)) of occurrence of the labels representing word W₃ given the occurrence of segment S_k of word W₁ ; and

the means for calculating the likelihood of occurrence of word W₁ comprises means for calculating the sum of the logarithms of the probabilities P(L_i (S_k (W₃))|S_k (W₂)) of occurrence of the labels representing word W₃ given the occurrence of segment S_k of word W₂.

12. A system as claimed in claim 10, further comprising:

means for generating maximum and minimum speech length information for word W₁ ;

means for generating maximum and minimum speech length information for word W₂ ;

means for determining the length of word W₃ ; and

means for setting the likelihood of occurrence of word W₁ substantially equal to zero if the length of word W₃ is (i) greater than the maximum speech length information for word W₁, or (ii) less than the minimum speech length information for word W₁ ; and

means for setting the likelihood of occurrence of word W₂ substantially equal to zero if the length of word W₃ is (i) greater than the maximum speech length information for word W₂, or (ii) less than the minimum speech length information for word W₂.