Sorenson IP Holdings, LLC

Methods, apparatus, systems, and articles of manufacture to translation between sign language and spoken language are disclosed. An example apparatus includes processor circuitry to at least one of instantiate or execute machine readable instructions to identify a plurality of candidate signs across different frames in video; associate a respective gloss to respective ones of the candidate signs; associate a respective confidence score with the respective glosses; identify overlapping frames of the candidate signs; select one or more of the candidate signs as performed signs based on the respective confidence scores and overlapping frames; and convert the performed signs to audio data.

A method may include obtaining first audio data of a first communication session between a first and second device and during the first communication session, obtaining a first text string that is a transcription of the first audio data and training a model of an automatic speech recognition system using the first text string and the first audio data. The method may further include in response to completion of the training, deleting the first audio data and the first text string and after deleting the first audio data and the first text string, obtaining second audio data of a second communication session between a third and fourth device and during the second communication session obtaining a second text string that is a transcription of the second audio data and further training the model of the automatic speech recognition system using the second text string and the second audio data.

A method of transcript presentation may include obtaining, at a device, transcript data that includes a transcription of audio data. The method may also include presenting, by a display of the device, the transcript data and obtaining, at the device, a revision to the transcript data. The method may further include obtaining an indication of a change to the presentation on the display of the device and in response to the indication of the change to the presentation, presenting, by the device, the revision.

A method may include obtaining a first audio signal including first speech originating at a remote device during a communication session between the remote device and a communication device and obtaining a second audio signal including second speech originating at the communication device during the communication session between the remote device and the communication device. The method may also include obtaining a characteristic of the communication session from one or more of: the first audio signal, the second audio signal, and settings of the communication device and determining a hearing level of a user of the communication device using the characteristic of the communication session.

A method may include obtaining a text string that is a transcription of audio data and selecting a sequence of words from the text string as a first word sequence. The method may further include encrypting the first word sequence and comparing the encrypted first word sequence to multiple encrypted word sequences. Each of the multiple encrypted word sequences may be associated with a corresponding one of multiple counters. The method may also include in response to the encrypted first word sequence corresponding to one of the multiple encrypted word sequences based on the comparison, incrementing a counter of the multiple counters associated with the one of the multiple encrypted word sequences and adapting a language model of an automatic transcription system using the multiple encrypted word sequences and the multiple counters.

A method of health assessment includes automatically establishing a communication session with a user device and recording audio from the user device obtained over the communication session. The method may also include providing the audio to a health assessment system configured to assess non-hearing health conditions of people using the audio and obtaining a health condition of a user of the user device from the health assessment system.

A method of transcript generation may include obtaining, from a device, audio data of a communication session between the device and another device. The method may also include directing the audio data to an automatic speech recognition system configured to generate transcript data that includes a transcription of the audio data. The method may further include providing the transcript data from the automatic speech recognition system to a large language model for the large language model to correct errors in the transcript data. Additionally, the method may include in response to providing the transcript data to the large language model, obtaining, from the large language model, correction data that includes correction of errors in the transcript data and directing, to the device, data based on the correction data.

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 may include obtaining first audio data of a first communication session between a first and second device and during the first communication session, obtaining a first text string that is a transcription of the first audio data and training a model of an automatic speech recognition system using the first text string and the first audio data. The method may further include in response to completion of the training, deleting the first audio data and the first text string and after deleting the first audio data and the first text string, obtaining second audio data of a second communication session between a third and fourth device and during the second communication session obtaining a second text string that is a transcription of the second audio data and further training the model of the automatic speech recognition system using the second text string and the second audio data.

A method may include obtaining audio that includes speech of a user. The method may also include acquiring, in real-time, a transcription of the audio. The transcription may include text of the speech in the audio. The method may further include obtaining a prediction based on the transcription of the audio. The prediction may include one or more words that are predicted to follow a last word in the transcription and the prediction may be continuously updated in response to continuous updates to the transcription. The method may also include presenting the prediction to the user such that the presented prediction continuously changes in response to continuous updates to the transcription.