Abstract: This application discloses an artificial intelligence-based (AI-based) wakeup word detection method performed by a computing device. The method includes: constructing, by using a preset pronunciation dictionary, at least one syllable combination sequence for self-defined wakeup word text inputted by a user; obtaining to-be-recognized speech data, and extracting speech features of speech frames in the speech data; inputting the speech features into a pre-constructed deep neural network (DNN) model, to output posterior probability vectors of the speech features corresponding to syllable identifiers; determine a target probability vector from the posterior probability vectors according to the syllable combination sequence; and calculate a confidence according to the target probability vector, and determine that the speech frames include the wakeup word text when the confidence is greater than or equal to a threshold.

Abstract: Disclosed are methods for the pre-treatment of lignocellulose by adding an alkali or acid reagent(s) during the densification thereof, and for the biotransformation thereof. In the method, an alkali reagent(s) or acid reagent(s) is added to a lignocellulosic raw material for a densification pre-treatment to form an alkali- or acid-containing densified lignocellulose with a compressed compact shape, thereby achieving the pre-treatment. The acid or alkali in the pre-treated lignocellulose can further pre-treat the lignocellulosic raw material in a mild manner during the subsequent transportation and storage processes. If a subsequent pre-treatment is needed, then the severity thereof is reduced substantially; in addition, the uniform mixing of the acid or alkali with the lignocellulose and a large density of the raw material promote a high efficiency and a high loading capacity of the subsequent pre-treatment of the densified lignocellulose. The method is simple and efficient.

Abstract: This application discloses an artificial intelligence-based (AI-based) wakeup word detection method performed by a computing device. The method includes: constructing, by using a preset pronunciation dictionary, at least one syllable combination sequence for self-defined wakeup word text inputted by a user; obtaining to-be-recognized speech data, and extracting speech features of speech frames in the speech data; inputting the speech features into a pre-constructed deep neural network (DNN) model, to output posterior probability vectors of the speech features corresponding to syllable identifiers; determine a target probability vector from the posterior probability vectors according to the syllable combination sequence; and calculate a confidence according to the target probability vector, and determine that the speech frames include the wakeup word text when the confidence is greater than or equal to a threshold.

Abstract: A biomass pretreatment method is provided to improve the bio-digestibility of lignocellulosic biomass. This pretreatment method densifies biomass with alkaline or acidic chemical(s) to obtain densified biomass containing chemicals. Pretreatment effects are realized during densification. The chemicals in densified biomass further react with biomass during biomass storage and transportation to improve the pretreatment effects. Further treatment (e.g. stream) can also be applied to the densified biomass to achieve better effects. As chemicals are mixed well with biomass during densification and the biomass density is greatly increased, further treatment is of high efficiency and high solid loading. This pretreatment method is simple and the densified biomass with chemicals is resistant to microbial contamination/degradation and thus facilitates storage and transportation.

Abstract: The present invention provides for the use of oleaginous yeast strains that are capable of converting lignocellulosic hydrolysates to lipids. More specifically, under specific molar carbon to nitrogen ratios of treated biomass hydrolysates, oleaginous yeasts are able to accumulate lipids that are suitable for the manufacture of biofuels and other products of interest. Additionally, some yeast species provided herein produce carotenoids when grown utilizing the disclosed methodologies.

Abstract: An integrated biological process for cellulosic bioproduct production is provided, which, in one embodiment, results in high ethanol productivity, enzyme recycling and reuse of yeast cells. The integrated process can be an integrated separate hydrolysis and fermentation (SHF) process or an integrated fast simultaneous saccharification and co-fermentation (FSSCF) process. The methods described herein can result in high bioproduct productivity through enzyme recycling and reuse of yeast cells.