Virtual reading companion technology to support the acquisition of reading fluency

A system of improving reading fluency by presenting a virtual reading partner that takes turns reading aloud with a reader, comprising:

• one or more data processors;
• a non-transitory computer-readable medium encoded with instructions for commanding the one or more data processors to execute steps of a process that include:
• receiving first audio data comprising speech from the reader recorded via a microphone and stored in a computer-readable medium, wherein the speech corresponds to the reader reading aloud from a first portion of a written transcript;
• processing the first audio data to identify spoken words from the speech using a processor-implemented automatic speech recognition module;
• comparing characteristics of the reader's speaking of words in the first portion of the written transcript to characteristics of correct speaking of the words in the first portion of the written transcript, said characteristics of correct speaking being received over a computer network;
• assessing, based on the comparing, a reading fluency of the reader;
• generating second audio data comprising (i) a pre-recorded narration of a second portion of the written transcript;
• or (ii) automatically generated text-to-speech of the second portion comprising a computer-simulated voice synthetization of the second portion, wherein a length of the second portion is based on the reading fluency, wherein the second audio data comprises a computer-simulated segment of the written transcript that is inversely proportional in length with the reading fluency, wherein the length of consecutive computer-simulated segments is adapted during cooperative reading of the written transcript when the reading fluency is detected to have changed during reading of the written transcript, and wherein the reading fluency decreases, the length of the adapted consecutive computer-simulated segments increases, wherein the reading fluency increases, the length of the adapted consecutive-simulated segments decreases;
• and
• presenting to the reader, the virtual reading partner based on audio playback and the adapted consecutive computer-simulated segments of the second audio data, wherein sound recording automatically resumes following presentation of the second audio data, wherein the virtual reading partner reading the second portion and the reader reading the first portion take turns reading aloud based on the length of the adapted consecutive-simulated segments until the end of the written transcript has been reached, wherein the length of the second portion is longer than a length of the first portion of the written transcript when the length of the adapted consecutive computer-simulated segments increases to a first threshold value, and wherein the length of the second portion is shorter than the length of the first portion of the written transcript when the length of the adapted consecutive computer-simulated segments decreases to a second threshold value.

A non-transitory computer-readable medium encoded with instructions for commanding one or more data processors to execute a method of improving reading fluency by presenting a virtual reading partner that takes turns reading aloud with a reader, the method comprising:

• receiving first audio data comprising speech from the reader recorded via a microphone and stored in a computer-readable medium, wherein the speech corresponds to the reader reading aloud from a first portion of a written transcript;
• processing the first audio data to identify spoken words from the speech using a processor-implemented automatic speech recognition module;
• comparing characteristics of the reader's speaking of words in the first portion of the written transcript to characteristics of correct speaking of the words in the first portion of the written transcript, said characteristics of correct speaking being received over a computer network;
• assessing, based on the comparing, a reading fluency of the reader;
• generating second audio data comprising (i) a pre-recorded narration of a second portion of the written transcript;
• or (ii) automatically generated text-to-speech of the second portion comprising a computer-simulated voice synthetization of the second portion, wherein a length of the second portion is based on the reading fluency, wherein the second audio data comprises a computer-simulated segment of the written transcript that is inversely proportional in length with the reading fluency, wherein the length of consecutive computer-simulated segments is adapted during cooperative reading of the written transcript when the reading fluency is detected to have changed during reading of the written transcript, and wherein the reading fluency decreases, the length of the adapted consecutive computer-simulated segments increases, wherein the reading fluency increases, the length of the adapted consecutive-simulated segments decreases;
• and
• presenting to the reader, the virtual reading partner based on audio playback and the adapted consecutive computer-simulated segments of the second audio data, wherein sound recording automatically resumes following presentation of the second audio data, wherein the virtual reading partner reading the second portion and the reader reading the first portion take turns reading aloud based on the length of the adapted consecutive-simulated segments until the end of the written transcript has been reached, wherein the length of the second portion is longer than a length of the first portion of the written transcript when the length of the adapted consecutive computer-simulated segments increases to a first threshold value, and wherein the length of the second portion is shorter than the length of the first portion of the written transcript when the length of the adapted consecutive computer-simulated segments decreases to a second threshold value.