Automatic Speech Recognition Using Limited Vocabulary: A Survey

Automatic Speech Recognition (ASR) is an active field of research due to its large number applications and the proliferation interfaces or computing devices that can support speech processing. However, bulk are based on well-resourced languages overshadow under-resourced ones. Yet, ASR represents undeniable means promote such languages, especially when designing human-to-human human-to-machine systems involving illiterate people. An approach design system targeting start with a limited vocabulary. using vocabulary subset recognition problem focuses small words sentences. This paper aims provide comprehensive view mechanisms behind as well techniques, tools, projects, recent contributions, possible future directions in work consequently provides way forward Although emphasis put vocabulary, most tools techniques reported this survey be applied general.AbbreviationsACC: Accuracy; AM: Acoustic Model; ASR: Recognition; BD-4SK-ASR: Basic Dataset for Sorani Kurdish CER: Character Error Rate; CMU: Carnegie Mellon University; CNN: Convolutional Neural Network; CNTK: CogNitive ToolKit; CUED: Cambridge University Engineering Department; DCT:Discrete Cosine Transformation; DL: Deep Learning; DNN: DRL: Reinforcement DWT: Discrete Wavelet Transform; FFT: Fast Fourier GMM: Gaussian Mixture HMM: Hidden Markov HTK: Model JASPER: Just Another Recognizer; LDA: Linear Discriminant Analysis; LER: Letter LGB: Light Gradient Boosting Machine; LM:Language LPC: Predictive Coding; LVCSR: Large Vocabulary Continuous LVQ: Learning Vector Quantization Algorithm; MFCC: Mel-Frequency Cepstrum Coefficient; ML: Machine PCM:Pulse-Code Modulation; PPVT: Peabody Picture Test; RASTA: RelAtive SpecTral; RLAT: Rapid Language Adaptation Toolkit; S2ST: Speech-to-Speech Translation; SAPI: Application Programming Interface; SDK: Software Development Kit; SVASR:Small WER: Word Rate