# US 2001/0027394 A1 · Method of identifying a language and of controlling a speech synthesis unit and a communication device

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2001/0027394 A1
- Document ID: US20010027394A1
- Status: Published application
- Kind: A1
- Application number: 09/751,161
- Filed: 2000-12-28
- Published: 2001-10-04
- Earliest claimed: 1999-12-30
- Assignees: Nokia Mobile Phones Ltd.
- Inventors: Wofgang Theimer
- Web page: https://patentgrep.com/patent/US20010027394A1

## CPC

- G06F 40/263: Language identification
- G06F 40/216: using statistical methods
- G10L 13/00: Speech synthesis; Text to speech systems
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 2015/223: {Execution procedure of a spoken command}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

The invention relates to a method of identifying a language in which a text is composed in the form of a string of characters, and also to a method of controlling a speech reproduction unit and to a communication device. To be able to carry out language identification with little expenditure, it is provided according to the invention that a frequency distribution (h1(x), h2(x,y), h3(x,y,z)) of letters in the text is ascertained, the ascertained frequency distribution (h1(x), h2(x,y), h3(x,y,z)) is compared with corresponding frequency distributions (l1(x), l2(x,y), l3(x,y,z)) of available languages, in order to ascertain similarity factors (s1, S2, s3) which indicate the similarity of the language of the text with the available languages, and the language for which the ascertained similarity factor (S1, S2, S3) is the greatest is established as the language of the text.

## Claims

### Claim 1

Method of identifying a language in which a text is composed as a string of characters, in which
a frequency distribution (h1(x), h2(x,y), h3(x,y,z)) of letters in the text is ascertained,
the ascertained frequency distribution (h1(x), h2(x,y), h3(x,y,z)) is compared with corresponding frequency distributions (l1(x), l2(x,y), l3(x,y,z)) of available languages, in order to ascertain similarity factors (S1, S2, S3) which indicate the similarity of the language of the text with the available languages, and
the language for which the ascertained similarity factor (s1, S2, S3) is the greatest is established as the language of the text.

### Claim 2 (depends on 1)

Method according to claim 1, characterized in that the language is only established if the greatest similarity factor (S1, S2, S3) ascertained is greater than a threshold value.

### Claim 3 (depends on 1, 2)

Method according to claim 1 or 2, characterized in that the ascertained frequency distribution (h1(x), h2(x,y), h3(x,y,z)) is stored as the frequency distribution (l1(x), l2(x,y), l3(x,y,z)) of a new language or is added to a corresponding frequency distribution (l1(x), l2(x,y), l3(x,y,z)) of a language if, in response to an inquiry, a language to which the ascertained frequency distribution (h1(x), h2(x,y), h3(x,y,z)) is to be assigned is indicated.

### Claim 4 (depends on 1, 2, 3)

Method according to claim 1, 2 or 3, characterized in that the ascertained frequency distribution (h1(x), h2(x,y), h3(x,y,z)) is added to the corresponding frequency distribution (l1(x), l2(x,y), l3(x,y,z)) of the language established.

### Claim 5

Method according to one of the preceding claims, characterized in that all non-letter characters, apart from spaces, are removed from the string of characters of the text, in order to ascertain from the string of characters thus obtained frequency distributions (h1(x), h2(x,y), h3(x,y,z)) of letters and groups of letters in the text.

### Claim 6

Method according to one of the preceding claims, characterized in that the length of the text is established and, depending on the length of the text, one, two or more frequency distributions (h1(x), h2(x,y), h3(x,y,z)) of letters and groups of letters in the text are ascertained.

### Claim 7 (depends on 6)

Method according to claim 6, characterized in that the length of the text is established as the number (H) of letters in the text and in that the number (H) of letters in the text is compared with the number (N) of letters in an alphabet, in order to determine which frequency distributions (h1(x), h2(x,y), h3(x,y,z)) are ascertained.

### Claim 8 (depends on 7)

Method according to claim 7, characterized in that the frequency distributions (h3(x,y,z), h2(x,y), h1(x)) of groups of letters with three letters, of groups of letters with two letters and of individual letters are ascertained if the number (H) of letters in the text is greater than the square (N2) of the number (N) of letters in the alphabet.

### Claim 9 (depends on 7, 8)

Method according to claim 7 or 8, characterized in that the frequency distributions (h2(x,y), h1(x)) of groups of letters with two letters and of individual letters are ascertained if the number (H) of letters in the text is greater than the number (N) of letters in the alphabet.

### Claim 10 (depends on 7, 8, 9)

Method according to claim 7, 8 or 9, characterized in that the frequency distribution (h1(x)) of individual letters is ascertained if the number (H) of letters in the text is less than the number (N) of letters in the alphabet.

### Claim 11

Method according to one of the preceding claims, characterized in that a complete alphabet is used, also including special letters of various languages based on Latin letters.

### Claim 12

Method according to one of the preceding claims, characterized in that the letters present in the text are investigated for special letters, in order to select according to the presence or absence of special letters characteristic of certain languages the languages which are to be taken into consideration in the comparison of the ascertained frequency distribution (h1(x), h2(x,y), h3(x,y,z)) with corresponding frequency distributions (l1(x), l2(x,y), l3(x,y,z)) of available languages.

### Claim 13

Method according to one of the preceding claims, characterized in that, after establishing the language, the letters present in the text are investigated for special letters which are characteristic of the language established and of languages not established, in order to confirm the language established.

### Claim 14

Method of controlling a speech reproduction unit (14), in which
a language identification according to one of the preceding claims is carried out for a text to be output in spoken form by means of a speech synthesis module (15) of the speech reproduction unit (14),
the language thereby established is transmitted to the speech reproduction unit (14), and
in the speech reproduction unit (14), the pronunciation rules of the language established are selected and used for the synthetic speech reproduction of the text by the speech synthesis module (15).

### Claim 15

Communication device with
a receiving module (10) for receiving, processing and managing information,
a speech synthesis module (15), which for the spoken output of texts is in connection with the receiving module (10), and
a language identification module (23), to which a text to be output by the speech synthesis module (15) can be fed for identifying the language in which the text to be output is composed, and which is connected to the speech synthesis module (15) for transmitting a language established for this text.

### Claim 16 (depends on 15)

Communication device according to claim 15, characterized in that pronunciation rules for various languages are stored in the speech synthesis module (15).

### Claim 17 (depends on 16)

Communication device according to claim 16, characterized in that a pronunciation-rules selection circuit (21) is provided in the speech synthesis module (15), which circuit is connected to the language identification module (23) and, depending on the language transmitted by the language identification module (23), selects the corresponding pronunciation rule, so that it can be used by a speech synthesis unit (17) of the speech synthesis module (15).

### Claim 18 (depends on 15, 16, 17)

Communication device according to claim 15, 16 or 17, characterized in that the language identification module (23) comprises a filter circuit (26), in order to remove all non-letter characters, apart from spaces, from a string of characters of a text.

### Claim 19 (depends on 15, 16, 17, 18)

Communication device according to one of claims 15 to 18, characterized in that the language identification module (23) comprises a statistics circuit (28), in order to ascertain a frequency distribution (h1(x), h2(x,y), h3(x,y,z)) of letters in the text.

### Claim 20 (depends on 19)

Communication device according to claim 19, characterized in that the statistics circuit (28) has first, second and third computing circuits (31, 32, 33), in order to ascertain frequency distributions (h1(x), h2(X,y), h3(x,y,z)) of individual letters, of groups of letters with two letters and of groups of letters with three letters.

### Claim 21 (depends on 15, 16, 17, 18, 19, 20)

Communication device according to one of claims 15 to 20, characterized in that the language identification module (23) has a comparator circuit (34), in order to compare for the ascertainment of similarity factors (S1, S2, S3) for a text ascertained frequency distributions (h1(x), h2(x,y), h3(x,y,z)) of letters with corresponding stored frequency distributions (l1(x), l2(x,y), l3(x,y,z)) of available languages.

### Claim 22 (depends on 21)

Communication device according to claim 21, characterized in that the language identification module (23) comprises an evaluation circuit (36), to which the similarity factors (S1, S2, S3) can be fed by the comparator circuit (34), in order to establish the language for which the ascertained similarity factor (S1, S2, S3) is greatest as the language of the text.
