Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview
Peter Bell, Joachim Fainberg, Ondřej Klejch, Jinyu Li, Steve Renals, Paweł Świętojański
Abstract
We present a structured overview of adaptation algorithms for neural network-based speech recognition, considering both hybrid hidden Markov model / neural network systems and end-to-end neural network systems, with a focus on speaker adaptation, domain adaptation, and accent adaptation. The overview characterizes adaptation algorithms as based on embeddings, model parameter adaptation, or data augmentation. We present a meta-analysis of the performance of speech recognition adaptation algorithms, based on relative error rate reductions as reported in the literature.
Topics & Concepts
Adaptation (eye)Computer scienceArtificial neural networkSpeech recognitionHidden Markov modelTime delay neural networkDomain adaptationAlgorithmArtificial intelligenceMachine learningClassifier (UML)PhysicsOpticsSpeech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing