Speech fluency evaluation and feedback tools are described. A computing device such as a smartphone may be used to collect speech (and/or other data). The collected data may be analyzed to detect various speech events (e.g., stuttering) and feedback may be generated and provided based on the detected speech events. The collected data may be used to generate a fluency score or other performance metric associated with speech. Collected data may be provided to a practitioner such as a speech therapist or physician for improved analysis and/or treatment.

An audio learning system, which is applied to a vehicle and provides a learning content to a user staying in the vehicle in audio manner, includes: a learning element storage unit storing multiple learning elements; an in-vehicle duration estimation unit estimating an in-vehicle duration during which the user is in the vehicle; a learning program generation unit generating one batch of a learning program to be completed within the in-vehicle duration estimated by the in-vehicle duration estimation unit by combining the plurality of learning elements; and an execution unit executing the learning program. When a driving load estimated by a driving load estimation unit is higher than a predetermined load, the learning program generation unit generates the learning program to mainly include the learning elements that have been executed.

An audio learning system, which is applied to a vehicle and provides a learning content to a user staying in the vehicle in audio manner, includes: a learning element storage unit storing multiple learning elements; an in-vehicle duration estimation unit estimating an in-vehicle duration during which the user is in the vehicle; a learning program generation unit generating one batch of a learning program to be completed within the in-vehicle duration estimated by the in-vehicle duration estimation unit by combining the plurality of learning elements; and an execution unit executing the learning program. When a driving load estimated by a driving load estimation unit is higher than a predetermined load, the learning program generation unit generates the learning program to mainly include the learning elements that have been executed.

An oral function visualization system includes: an outputter that outputs information for prompting a user to utter a predetermined voice; an obtainer that obtains an uttered voice of the user uttered in accordance with the output; an analyzer that analyzes the uttered voice obtained by the obtainer; and an estimator that estimates a state of oral organs of the user from a result of analysis of the uttered voice by the analyzer. The outputter outputs, based on the state of the oral organs of the user estimated by the estimator, information for the user to achieve a state of the oral organs suitable for utterance of the predetermined voice.

A method and system for detecting errors when practicing fluency shaping exercises. The method includes setting each threshold of a set of thresholds to a respective predetermined initial value; analyzing a voice production to compute a set of first energy levels composing the voice production, wherein the voice production is of a user practicing a fluency shaping exercise; detecting at least one speech-related error based on the computed set of first energy levels, a set of second energy levels, and the set of thresholds, wherein the detection of the at least one speech-related error is with respect to the fluency shaping exercise being practiced by the user, wherein the set of second energy levels is determined based on a calibration process; and generating feedback indicating the detected at least one speech-related error.

A method and system for detecting errors when practicing fluency shaping exercises. The method includes setting each threshold of a set of thresholds to a respective predetermined initial value; analyzing a voice production to compute a set of first energy levels composing the voice production, wherein the voice production is of a user practicing a fluency shaping exercise; detecting at least one speech-related error based on the computed set of first energy levels, a set of second energy levels, and the set of thresholds, wherein the detection of the at least one speech-related error is with respect to the fluency shaping exercise being practiced by the user, wherein the set of second energy levels is determined based on a calibration process; and generating feedback indicating the detected at least one speech-related error.

A machine-delivered aural cloze exercise makes use of natural, connected speech and allows for a portion of the audio to be selected and obfuscated during playback, creating an aural cloze portion. The aural cloze portion is extended beyond its natural length an effective amount to make the exercise clear to the user. If the audio is accompanied by video, the video is extended uniformly during the aural cloze portion, and optionally, can also be obfuscated during the aural cloze portion.

A machine-delivered aural cloze exercise makes use of natural, connected speech and allows for a portion of the audio to be selected and obfuscated during playback, creating an aural cloze portion. The aural cloze portion is extended beyond its natural length an effective amount to make the exercise clear to the user. If the audio is accompanied by video, the video is extended uniformly during the aural cloze portion, and optionally, can also be obfuscated during the aural cloze portion.

The present invention provides methods and systems determining the behavioural index of a user. The present invention involves analyzing the user's behaviour and linguistic parameters using a smart wearable device. Basis the analysis, user's behavioural index is suitably determined, modified and informed to the user.

Provided is a technique for effectively searching for a book for an articulation disordered-child to use in practice. A search condition setting unit 120 sets a search condition for a speech sound in accordance with a selection state of kana symbol buttons disposed in a book search screen, the kana symbol buttons corresponding one-to-one to kana symbols indicating respective speech sounds. A search unit 130 searches for a book in which a desired speech sound appears, in accordance with the search condition. A book search screen includes at least one of a Japanese syllabary button group in which the kana symbol buttons are classified as vowels or consonants, and an articulation button group in which the kana symbol buttons are classified by articulatory organ and articulation manner.