A method for automatically delaying playback of a voice message at a captioning device may include receiving, at a captioning device, a request from a user to play back a voice message that is stored on the captioning device. The method may also include, in response to the request from the user, automatically delaying the playback of the voice message, at the captioning device, until an establishment of a connection between the captioning device and a remote call assistant, in order to allow the remote call assistant to caption on the captioning device, in real-time, the voice message from the very beginning of the playback of the voice message.

A system and method for presenting substantially simultaneous voice and text to an assisted user (AU) during a voice conversation between the AU and a hearing user (HU), the hearing user using an HU device to talk to the assisted user, the system comprising an AU captioned device including a device processor, a relay that includes a relay display, a relay speaker and a relay processor, wherein, at least one of the device processor and the relay processor is programmed to perform the steps of receiving an HU voice signal comprising a sequence of HU voice segments and assigning time stamps to each of the HU voice segments, wherein, the relay processor is programmed to perform the steps of generating text segments corresponding to each HU voice segment, storing each HU voice segment along with a corresponding text segment and a corresponding time stamp in a memory device, broadcasting the HU voice segments to a call assistant (CA) via the relay speaker and presenting each text segment via the relay display substantially contemporaneously with broadcast of the corresponding HU voice segment.

Apparatuses and methods are disclosed for automatically connecting to a relay service and establish a captioning communication session during a call between a hearing-impaired user and a far-end user. The apparatus includes communication elements configured to receive captions from a relay service, and a processor configured to automatically connect to the relay service and establish a captioning communication session during a call responsive to a determination that a connection to the relay service failed during a time in which the hearing-impaired user desired captions to be enabled. A method includes determining captions are desired by the hearing-impaired user at a first time to be enabled for display to the communication device during a call, detecting a failed connection to the relay service at a second time, and automatically connecting with the relay service and establishing a new captioning communication session at a third time during the call.

A method and system for providing captioned telephone service, the method comprising the steps of, initiating a first captioned telephone service call, during the first captioned telephone service call, creating a first set of captions using a call assistant, simultaneous with creating the first set of captions using a call assistant, creating a second set of captions using an automated speech recognition engine, comparing the first set of captions and the second set of captions using a scoring algorithm based on errors between the first and second sets of captions to generate a score for the second set of captions, in response to the score being within a predetermined threshold range, continuing the call using only the automated speech recognition engine to generate text and in response to the score being outside of the predetermined threshold range, continuing the call using a call assistant to generate captions.

A call captioning system for captioning a hearing user's (HU's) voice signal during an ongoing call with an assisted user (AU) includes: an AU communication device with a display screen and a caption service activation feature, and a first processor programmed to, during an ongoing call, receive the HU's voice signal. Prior to activating the caption service via the activation feature, the processor uses an automated speech recognition (ASR) engine to generate HU voice signal captions, detect errors in the HU voice signal captions, use the errors to train the ASR software to the HU's voice signal to increase accuracy of the HU captions generated by the ASR engine; and store the trained ASR engine for subsequent use. Upon activating the caption service during the ongoing call, the processor uses the trained ASR engine to generate HU voice signal captions and present them to the AU via the display screen.

A system is provided that includes a first network interface for a first network type and a second network interface for a second network type that is different from the first network type. The system also includes at least one processor configured to cause the system to perform operations. The operations may include obtaining, from the first network interface, audio from a communication session with a remote device established over the first network and obtaining an indication of a communication device available to participate in the communication session and direct audio obtained from the communication session to a remote transcription system. The operations may also include directing the audio to the second network interface for transmission to the communication device, obtaining transcript data from the remote transcription system based on the audio, and directing the transcript data to the second network interface for transmission to the communication device.

A method for maintaining contact information in a hearing impaired assisted user's communication device includes the steps of (a) providing a web site for altering assisted user contact information, (b) linking a proxy device to the web site, (c) receiving an identifier associated with the assisted user's device via the proxy device, (d) identifying an assisted user's device via the received identifier, (e) enabling the proxy device to be used to modify contact information for the assisted user associated with the received identifier, (f) starting a timer to time out a sync timeout period, (g) during the sync timeout period, receiving an indication via the assisted user's device confirming a desire to update the assisted user's contact information, (h) updating the assisted user's contact information, and (i) at the end of the timeout period, ceasing an indication that updated data is ready to be used from the assisted user's device.

A method to transcribe communications includes the steps of obtaining a plurality of hypothesis transcriptions of a voice signal generated by a speech recognition system, determining consistent words that are included in at least first and second of the plurality of hypothesis transcriptions, in response to determining the consistent words, providing the consistent words to a device for presentation of the consistent words to an assisted user, and presenting the consistent words via a display screen on the device, wherein a rate of the presentation of the words on the display screen is variable.

A method and system for assessing captioning quality of a call assistant (CA) that transcribes a hearing user's (HU's) voice signal during a call with an assisted user (AU) into caption text, the method comprising the steps of receiving an HU voice signal at a relay, providing the HU voice signal to a first CA to transcribe into first caption text, providing the first caption text to a second CA for correction, the text corrected by the second CA being a true text caption and comparing the first caption text to the true text caption to identify a quality factor associated with the first caption text.

A captioning system comprising a processor and a memory having stored thereon software such that, when the software is executed by the one or more processors, the system generates text captions from speech data, including at least the following, receiving, from a hearing user's (HU's) device, an HU's speech data, generating, at the one or more hardware processors, first text captions from the speech data using a speech recognition algorithm, automatically determining, at the one or more processors, whether the generated first text captions meet a first accuracy threshold and when the first text captions meet the first accuracy threshold, sending the first text captions to an assisted user's (AU's) device for display, when the first text captions do not meet the first accuracy threshold, generating, at the one or more processors, second text captions from the speech data based on user input to the speech recognition algorithm from a call assistant and sending the second text captions to the AU's device for display.