US 11,900,072 B1 · Quick lookup for speech translation

Abstract

Offered is a system that presents on a display screen a translation of a sentence together with an untranslated version of the sentence, and that can cause both of the displayed sentences to break apart into component parts in response to a simple user action, e.g., double-tapping on one of them. When the user selects (e.g., taps on) any portion of either version of the sentence, the system can identify a corresponding portion of the other version (in the other language). In some implementations, a user device can include both a microphone and a display screen, and an automatic speech recognition (ASR) engine can be used to transcribe the user's speech in one language (e.g., English) into text. The system can translate the resulting text into another language (e.g., Spanish) and display the translated text on the display screen along with the untranslated text. When a user selects a portion of a sentence, the system can also present information about the selected portion (e.g., a dictionary definition) and/or enable selection of a modification to the selected portion (e.g., a different one of the N-best results that were generated by a translation service or an automatic speech recognition (ASR) service).

Claims24

Dependent claims

An apparatus, comprising:

a screen;
at least one processor;
and
at least one computer-readable medium encoded with instructions that, when executed by the at least one processor, cause the apparatus to:
display, on the screen, first text corresponding to a first version of a sentence in a first language;
display, on the screen, second text corresponding to a second version of the sentence in a second language;
indicate, on the screen, that two or more first segments of the first text and two or more second segments of the second text are individually selectable;
detect, while the two or more first segments and the two or more second segments are simultaneously indicated as being individually selectable, user selection of one of the first segments;
indicate, on the screen, the selected one of the first segments;
indicate, on the screen, one or more of the second segments that correspond to a translation of the selected one of the first segments;
detect, while the two or more first segments and the two or more second segments are indicated as being individually selectable, user selection of one of the second segments;
indicate, on the screen, the selected one of the second segments;
and
indicate, on the screen, one or more of the first segments that correspond to a translation of the selected one of the second segments.

11 more elements

An apparatus, comprising:

a screen;
at least one processor;
and
at least one computer-readable medium encoded with instructions that, when executed by the at least one processor, cause the apparatus to:
display, on the screen, at least a first text segment, the first text segment including first text, wherein the first text segment is included in a first version of a sentence in a first language;
send a representation of the first version of the sentence to a remote computing system for machine translation into a second version of the sentence in a second language;
display, on the screen, second text included in the second version of the sentence;
indicate, on the screen, that the first text segment is individually selectable;
detect, while the first text segment is indicated as being individually selectable, a first type of user action selecting the first text segment;
in response to detecting the first type of user action selecting the first text segment, display, on the screen, first information corresponding to the first text segment;
detect, while the first text segment is indicated as being individually selectable, a second type of user action selecting the first text segment, the second type of user action including a double tap, a long tap, a double click, or a long click;
and
in response to detecting the second type of user action selecting the first text segment, indicate, on the screen, that two or more segments of the first text are individually selectable, wherein the second type of user action is different than the first type of user action, and each of the two or more segments of the first text is shorter than the first text segment.

10 more elements

A computer-implemented method, comprising:

displaying, on a screen, at least a first text segment, the first text segment including first text, wherein the first text segment is included in a first version of a sentence in a first language;
sending a representation of the first version of the sentence to a remote computing system for machine translation into a second version of the sentence in a second language;
displaying, on the screen, second text included in the second version of the sentence;
indicating, on the screen, that the first text segment is individually selectable;
detecting, while the first text segment is indicated as being individually selectable, a first type of user action selecting the first text segment;
in response to detecting the first type of user action selecting the first text segment, displaying, on the screen, first information corresponding to the first text segment;
detecting, while the first text segment is indicated as being individually selectable, a second type of user action selecting the first text segment, the second type of user action including a double tap, a long tap, a double click, or a long click;
and
in response to detecting the second type of user action selecting the first text segment, indicating, on the screen, that two or more segments of the first text are individually selectable, wherein the second type of user action is different than the first type of user action, and each of the two or more segments of the first text is shorter than the first text segment.

6 more elements

Dependencies are inferred from the claim text.

Quick lookup for speech translation

Life of this patent

Quick lookup for speech translation

Life of this patent

Abstract

Claims24