Sequence memoizer based language model for Russian speech recognition
نویسندگان
چکیده
In this paper, we propose a novel language model for Russian large vocabulary speech recognition based on sequence memoizer modeling technique. Sequence memoizer is a long span text dependency model and was initially proposed for character language modeling. Here, we use it to build word level language model (LM) in ASR. We compare its performance with recurrent neural network (RNN) LM, which also models long span word dependencies. A number of experiments were carried out using various amounts of train data and different text data arrangements. According to our experimental results, the sequence memoizer LM outperforms recurrent neural network and standard 3-gram LMs in terms of perplexity, while RNN LM achieves better word error rate. The lowest word error rate is achieved by combining all three language models together using linear interpolation. Index Terms sequence memoizer, advanced language modeling, inflective languages
منابع مشابه
Vision - Based Hand - Gesture Applications Against Cyberterrorism Finding
Probabilistic models of sequences play a central role inmost machine translation, automated speech recognition,lossless compression, spell-checking, and gene identifica-tion applications to name but a few. Unfortunately, real-world sequence data often exhibit long range dependencieswhich can only be captured by computationally challeng-ing, complex models. Sequence d...
متن کاملNoospheric Psychological-Educational Paradigm as a Methodological Basis for Teaching Russian-Language Business Communication to Foreign Students
In the context of the polyparadigmatic system of higher education, the noospheric psychological-pedagogical paradigm is considered, on its basis a lingvodidactic model is developed for the formation of professional-communicative competence (PCC) in Russian-language business communication among foreign students. The research focuses on the basic principles of the noospheric paradigm, which procl...
متن کاملمقایسه روش های طیفی برای شناسایی زبان گفتاری
Identifying spoken language automatically is to identify a language from the speech signal. Language identification systems can be divided into two categories, spectral-based methods and phonetic-based methods. In the former, short-time characteristics of speech spectrum are extracted as a multi-dimensional vector. The statistical model of these features is then obtained for each language. The ...
متن کاملImprovements to the Sequence Memoizer
The sequence memoizer is a model for sequence data with state-of-the-art performance on language modeling and compression. We propose a number of improvements to the model and inference algorithm, including an enlarged range of hyperparameters, a memory-efficient representation, and inference algorithms operating on the new representation. Our derivations are based on precise definitions of the...
متن کاملPersian Phone Recognition Using Acoustic Landmarks and Neural Network-based variability compensation methods
Speech recognition is a subfield of artificial intelligence that develops technologies to convert speech utterance into transcription. So far, various methods such as hidden Markov models and artificial neural networks have been used to develop speech recognition systems. In most of these systems, the speech signal frames are processed uniformly, while the information is not evenly distributed ...
متن کامل