An embodiment for speech-to-text auto-scaling of computational resources is provided. The embodiment may include computing a delta for each word in a transcript between a wall clock time and a time when the word is delivered to a client. The embodiment may also include submitting the deltas to a group of metrics servers. The embodiment may further include requesting from the group of metrics servers current values of the deltas. The embodiment may also include determining whether the current values of the deltas exceed a pre-defined max-latency threshold. The embodiment may further include adjusting the allocated computational resources based on a frequency of the current values of the deltas that exceed the pre-defined max-latency threshold. The embodiment may also include creating a histogram from the current values of the deltas and scaling-up the allocated computational resources based on a percentage of data points that fall above the pre-defined max-latency threshold.

A method of training a custom hotword model includes receiving a first set of training audio samples. The method also includes generating, using a speech embedding model configured to receive the first set of training audio samples as input, a corresponding hotword embedding representative of a custom hotword for each training audio sample of the first set of training audio samples. The speech embedding model is pre-trained on a different set of training audio samples with a greater number of training audio samples than the first set of training audio samples The method further includes training the custom hotword model to detect a presence of the custom hotword in audio data. The custom hotword model is configured to receive, as input, each corresponding hotword embedding and to classify, as output, each corresponding hotword embedding as corresponding to the custom hotword.

[Problem] Provided is a presentation support system that makes it possible to give effective presentations, for both presentations by machines and normal presenters. [Solution] The presentation support system included: a display unit 3; a material storage unit 5 that stores a presentation material and a plurality of keywords; an audio storage unit 7; an audio analysis unit 9 that analyzes a term contained in a presentation; a keyword order adjustment unit 11 that analyzes an order of appearance of a plurality of keywords contained in the audio analyzed by the audio analysis unit and changes the order of the plurality of keywords on the basis of the order of appearance; and a display control unit 13 that controls content displayed in the display unit 3.

An electronic device includes a controller. The controller performs a speech word analysis based on the voice of a user after performing a first voice output request. The controller estimates a comprehension level of the user, based on information linked to a word stored in the memory and a result of the speech word analysis, and then performs a second voice output request in accordance with the comprehension level of the user. When the mobile terminal configured to output the first voice and the second voice is mounted on a charging stand, the controller may perform the speech word analysis, estimate the comprehension level, and perform the second voice output request.

An audio processing device for speech recognition is provided, which includes a memory circuit, a power spectrum transfer circuit, and a feature extraction circuit. The power spectrum transfer circuit is coupled to the memory circuit, reads frequency spectrum coefficients of time-domain audio sample data from the memory circuit, generates compressed power parameters by performing a power spectrum transfer processing and a compressing processing according to the frequency spectrum coefficients, and writes the compressed power parameters into the memory circuit. The feature extraction circuit is coupled to the memory circuit, reads the compressed power parameters from the memory circuit, generates an audio feature vector by performing mel-filtering and frequency-to-time transfer processing according to the compressed power parameters. The bit width of the compressed power parameters is less than the bit width of the frequency spectrum coefficients.

A method includes receiving audio data encoding an utterance spoken by a native speaker of a first language, and receiving a biasing term list including one or more terms in a second language different than the first language. The method also includes processing, using a speech recognition model, acoustic features derived from the audio data to generate speech recognition scores for both wordpieces and corresponding phoneme sequences in the first language. The method also includes rescoring the speech recognition scores for the phoneme sequences based on the one or more terms in the biasing term list, and executing, using the speech recognition scores for the wordpieces and the rescored speech recognition scores for the phoneme sequences, a decoding graph to generate a transcription for the utterance.

An embodiment for speech-to-text auto-scaling of computational resources is provided. The embodiment may include computing a delta for each word in a transcript between a wall clock time and a time when the word is delivered to a client. The embodiment may also include submitting the deltas to a group of metrics servers. The embodiment may further include requesting from the group of metrics servers current values of the deltas. The embodiment may also include determining whether the current values of the deltas exceed a pre-defined max-latency threshold. The embodiment may further include adjusting the allocated computational resources based on a frequency of the current values of the deltas that exceed the pre-defined max-latency threshold. The embodiment may also include creating a histogram from the current values of the deltas and scaling-up the allocated computational resources based on a percentage of data points that fall above the pre-defined max-latency threshold.

To provide an electronic device, which is carried by a user and is provided with a voice input unit, provided with a detection unit detecting a proximity state of the electronic device and the user and a control unit controlling the detection sensitivity of a voice input unit according to a detection result by the detection unit. Preferably, the detection unit detects a wearing state of the electronic device by the user and, when a non-wearing state where is detected by the detection unit, the control unit increases the detection sensitivity of the voice input unit to be higher than the detection sensitivity of the voice input unit in the wearing state.

Methods, devices, and systems for processing audio information are disclosed. An exemplary method includes receiving an audio stream. The audio stream may be monitored by a low power integrated circuit. The audio stream may be digitized by the low power integrated circuit. The digitized audio stream may be stored in a memory, wherein storing the digitized audio stream comprises replacing a prior digitized audio stream stored in the memory with the digitized audio stream. The low power integrated circuit may analyze the stored digitized audio stream for recognition of a keyword. The low power integrated circuit may induce a processor to enter an increased power usage state upon recognition of the keyword within the stored digitized audio stream. The stored digitized audio stream may be transmitted to a server for processing. A response received from the server based on the processed audio stream may be rendered.

An electronic device can implement a zero-latency digital assistant by capturing audio input from a microphone and using a first processor to write audio data representing the captured audio input to a memory buffer. In response to detecting a user input while capturing the audio input, the device can determine whether the user input meets a predetermined criteria. If the user input meets the criteria, the device can use a second processor to identify and execute a task based on at least a portion of the contents of the memory buffer.