# US 2021/0279431 A1 · Bidirectional call translation in controlled environment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0279431 A1 - Document ID: US20210279431A1 - Status: Published application - Kind: A1 - Application number: 17/146,848 - Filed: 2021-01-12 - Published: 2021-09-09 - Earliest claimed: 2017-07-12 - Assignees: Global Tel*Link Corporation - Applicants: Global Tel*Link Corporation - Inventors: Stephen L. HODGE - Web page: https://patentgrep.com/patent/US20210279431A1 ## CPC - G06F 40/58: Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation - H04M 3/42: Systems providing special services or facilities to subscribers (specially adapted for wireless communication networks H04W4/00) - H04M 2203/2061: Language aspects - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08) ## Abstract A call translation system and a method for operating the management system in a controlled environment is disclosed. The call translation system includes a calling device and a call translation server. The calling device receives authorization from the call translation server to conduct call sessions within the controlled environment. The calling device further receives a call session application from the call translation server that enables the calling device to initiate and establish call sessions through the call translation server. The call session application allows a user of the calling device to select outside parties to add to the call session. ## Claims ### Claim 1 (canceled) ### Claim 2 A method for improving efficiency of bidirectional language translation by a call translation server associated with a controlled environment, comprising: receiving a call session between a first calling device located within the controlled environment and a second calling device, wherein the call session includes voice data and translated voice data, wherein the translated voice data is based on a translation of the voice data by the call translation server, and wherein the first calling device is associated with a user in the controlled environment; storing the voice data and the translated voice data in a user profile associated with the user; generating user speech metrics based on a speech analysis of the voice data and the translated voice data, wherein the user speech metrics are associated with the user; and training, using the user speech metrics, the call translation server to improve bidirectional language translation of speech associated with the user. ### Claim 3 (depends on 2) The method of claim 2, further comprising: storing the user speech metrics in the user profile. ### Claim 4 (depends on 2) The method of claim 2, further comprising: translating the voice data based on the user speech metrics. ### Claim 5 (depends on 4) The method of claim 4, wherein the user speech metrics include a user cadence, wherein the cadence represents a speech speed of the user and wherein the cadence is calculated based on the voice data and prior voice data stored from a prior call session. ### Claim 6 (depends on 5) The method of claim 5, wherein translating the voice data based on the user speech metrics further comprises: detecting, based on the speech speed, a stop in the voice data; and initiating the translating based on the detecting. ### Claim 7 (depends on 4) The method of claim 4, wherein the user speech metrics include a word/phrase frequency, wherein the word/phrase frequency represents usage of a word or phrase by the user and wherein the word/phrase frequency is calculated based on the voice data and prior voice data stored from a prior call session. ### Claim 8 (depends on 7) The method of claim 7, wherein translating the voice data based on the user speech metrics further comprises: determining that a word in the voice data matches a corresponding word in the word/phrase frequency; and retrieving a pre-translated word based on the determining, wherein the pre-translated word was generated prior to the translating. ### Claim 9 (depends on 4) The method of claim 4, wherein the user speech metrics include an intonation, wherein the intonation represents a voice pitch of the user and wherein the intonation is calculated based on the voice data and prior voice data stored from a prior call session. ### Claim 10 A call translation server within a controlled environment, comprising: a memory; and a processor coupled to the memory, the processor configured to: receive a call session between a first calling device located within the controlled environment and a second calling device, wherein the call session includes voice data and translated voice data, wherein the translated voice data is based on a translation of the voice data by the translation server, and wherein the first calling device is associated with a user in the controlled environment; store the voice data and the translated voice data in a user profile associated with the user; generate user speech metrics based on a speech analysis of the voice data and the translated voice data, wherein the user speech metrics are associated with the user; and train, using the user speech metrics, the translation server to improve bidirectional language translation of speech associated with the user. ### Claim 11 (depends on 10) The call translation server of claim 10, wherein the processor is further configured to: store the user speech metrics in the user profile. ### Claim 12 (depends on 10) The call translation server of claim 10, wherein the processor is further configured to: translating the voice data based on the user speech metrics. ### Claim 13 (depends on 12) The call translation server of claim 12, wherein the user speech metrics include a user cadence, wherein the cadence represents a speech speed of the user and wherein the cadence is calculated based on the voice data and prior voice data stored from a prior call session. ### Claim 14 (depends on 13) The call translation server of claim 13, wherein to translate the voice data based on the user speech metrics, the processor is further configured to: detect, based on the speech speed, a stop in the voice data; and initiate the translating based on the detecting. ### Claim 15 (depends on 10) The call translation server of claim 10, wherein the user speech metrics include a word/phrase frequency, wherein the word/phrase frequency represents usage of a word or phrase by the user and wherein the word/phrase frequency is calculated based on the voice data and prior voice data stored from a prior call session. ### Claim 16 (depends on 15) The call translation server of claim 15, wherein to translate the voice data based on the user speech metrics, the processor is further configured to: determine that a word in the voice data matches a corresponding word in the word/phrase frequency; and retrieve a pre-translated word based on the determining, wherein the pre-translated word was generated prior to the translating. ### Claim 17 A non-transitory computer-readable medium having instructions stored therein, which when executed by a processor in a call translation server cause the processor to perform operations, the operations comprising: receiving a call session between a first calling device located within a controlled environment and a second calling device, wherein the call session includes voice data and translated voice data, wherein the translated voice data is based on a translation of the voice data by the translation server, and wherein the first calling device is associated with a user in the controlled environment; storing the voice data and the translated voice data in a user profile associated with the user; generating user speech metrics based on a speech analysis of the voice data and the translated voice data, wherein the user speech metrics are associated with the user; and training, using the user speech metrics, the translation server to improve bidirectional language translation of speech associated with the user. ### Claim 18 (depends on 17) The non-transitory computer-readable medium of claim 17, the operations further comprising: storing the user speech metrics in the user profile. ### Claim 19 (depends on 17) The non-transitory computer-readable medium of claim 17, the operations further comprising: translating the voice data based on the user speech metrics. ### Claim 20 (depends on 19) The non-transitory computer-readable medium of claim 19, wherein the user speech metrics include a user cadence, wherein the cadence represents a speech speed of the user and wherein the cadence is calculated based on the voice data and prior voice data stored from a prior call session. ### Claim 21 (depends on 20) The non-transitory computer-readable medium of claim 20, wherein to translate the voice data based on the user speech metrics, the processor is further configured to: detecting, based on the speech speed, a stop in the voice data; and initiating the translating based on the detecting.