Captioned telephone service system for user with speech disorder

A user's device for receiving a transcription service and a speech-to-text and text-to-speech converting service to a user with a hearing impairment and a speech disorder during a phone call between the user and a peer by using a captioned telephone service (“CTS”) system, the user's device comprising:

• a user application installed on the user's device, wherein the user's device is constructed to be connected to a CTS server for the phone call between the user's device and a peer's device,
• wherein the CTS system comprises a database, which is associated with the user and stores user's spoken audio and corresponding text,
• wherein the CTS system comprises a speech-to-text handler and a text-to-speech handler, wherein the speech-to-text handler is configured to transcribe user's voice into text based at least in part on the database, wherein the text-to-speech handler is configured to convert the text into a speech which is then sent to the peer's device,
• wherein the user application is configured to provide a training text to the user to read so that the user's spoken audio is saved together with the training text, which corresponds to the user's spoken audio, in the database, and wherein the user application is configured to display the text transcribed from the user's voice by the speech-to-text handler,
• wherein the user application is configured to provide a training text to the user to read so that the user's spoken audio is saved together with the training text, which corresponds to the user's spoken audio, in the database, wherein the user application provides a ready button next to the training text so that the user presses the ready button and then begins to read the training text to be recorded, and wherein once the ready button is pressed, the ready button is configured to be changed to a completed button so that the user presses the completed button once he finishes reading the training text.

An audio preprocessor for providing a speech-to-text and text-to-speech converting service to a user with a hearing impairment and a speech disorder during a phone call between the user and a peer, the audio preprocessor comprising:

• a controller;
• a database, which is associated with the user and stores user's spoken audio and corresponding text;
• an audio input unit;
• a speech-to-text handler;
• a text-to-speech handler;
• and
• an audio output unit,
• wherein the audio preprocessor is constructed to be connected to a user's device and a peer's device for the phone call between the user's device and the peer's device,
• wherein the audio input unit receives a user's voice from the user's device,
• wherein the speech-to-text handler is configured to transcribe the user's voice into text based at least in part on the database,
• wherein the text-to-speech handler is configured to convert the text into a speech,
• wherein the audio output unit receives the speech and sends it to the peer's device,
• wherein the audio preprocessor is configured to provide a training text to the user's device in order for the user to read it so that the user's spoken audio is saved together with the training text, which corresponds to the user's spoken audio, in the database,
• wherein the speech-to-text handler uses a speech recognition system, which has database of the speech recognition system, to transcribe the user's voice into the text, and
• wherein the speech-to-text handler assigns greater weight to data of the database of the CTS system than data of the database of the speech recognition system in transcribing the user's voice into the text.