Devices and techniques are generally described for cohort determination in natural language processing. In various examples, a first natural language input to a natural language processing system may be determined. The first natural language input may be associated with a first account identifier. A first machine learning model may determine first data representing one or more words of the first natural language input. A second machine learning model may determine second data representing one or more acoustic characteristics of the first natural language input. Third data may be determined, the third data including a predicted performance for processing the first natural language input by the natural language processing system. The third data may be determined based on the first data representation and the second data representation.

An instance weighted learning (IWL) machine learning model. In one example embodiment, a method of employing an IWL machine learning model to train a classifier may include determining a quality value that should be associated with each machine learning training instance in a temporal sequence of reinforcement learning machine learning training instances, associating the corresponding determined quality value with each of the machine learning training instances, and training a classifier using each of the machine learning training instances. Each of the machine learning training instances includes a state-action pair and is weighted during the training based on its associated quality value using a weighting factor that weights different quality values differently such that the classifier learns more from a machine learning training instance with a higher quality value than from a machine learning training instance with a lower quality value.

Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.

Specification covers new algorithms, methods, and systems for artificial intelligence, soft computing, and deep learning/recognition, e.g., image recognition (e.g., for action, gesture, emotion, expression, biometrics, fingerprint, facial, OCR (text), background, relationship, position, pattern, and object), large number of images (“Big Data”) analytics, machine learning, training schemes, crowd-sourcing (using experts or humans), feature space, clustering, classification, similarity measures, optimization, search engine, ranking, question-answering system, soft (fuzzy or unsharp) boundaries/impreciseness/ambiguities/fuzziness in language, Natural Language Processing (NLP), Computing-with-Words (CWW), parsing, machine translation, sound and speech recognition, video search and analysis (e.g. tracking), image annotation, geometrical abstraction, image correction, semantic web, context analysis, data reliability (e.g., using Z-number (e.g., “About 45 minutes; Very sure”)), rules engine, control system, autonomous vehicle, self-diagnosis and self-repair robots, system diagnosis, medical diagnosis, biomedicine, data mining, event prediction, financial forecasting, economics, risk assessment, e-mail management, database management, indexing and join operation, memory management, and data compression.