An Improvement of robustness to speech loudness change for an ASR system based on LC-RC features
نویسندگان
چکیده
This paper deals with new front-end feature improvements for Automatic Speech Recognition (ASR) robustness to changes in speech loudness. Our experiments show that applying a RASTA– like filter gives a significant improvement in robustness to speech loudness change, leading to an up to 4% PER reduction.
منابع مشابه
بهبود عملکرد سیستم بازشناسی گفتار پیوسته بوسیله ویژگی‌های استخراج شده از مانیفولدهای گفتاری در فضای بازسازی شده فاز
The design for new feature extraction methods out of the speech signal and combination of their obtained information is one of the most effective approaches to improve the performance of automatic speech recognition (ASR) system. Recent researches have been shown that the speech signal contains nonlinear and chaotic properties, but the effects of these properties are not used in the continuous ...
متن کاملThe Lee Silverman Voice Treatment Improves Vocal loudness in Early Persian Parkinson’s Patients: A Pilot Study
Objectives: In the early stages, most Parkinson’s patients display some degrees of voice and speech disorders. Speech disorders can negatively affect social interactions and human life, thus treatment plans for the disorders in the early stages might be further beneficial than the late stages. Therefore, we aimed to investigate on the effect of an intervention on Persian patients with early mil...
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 کاملمقایسه روش‌های مختلف یادگیری ماشین در خلاصه‌سازی استخراجی گفتار به گفتار فارسی بدون استفاده از رونوشت
In this paper, extractive speech summarization using different machine learning algorithms was investigated. The task of Speech summarization deals with extracting important and salient segments from speech in order to access, search, extract and browse speech files easier and in a less costly manner. In this paper, a new method for speech summarization without using automatic speech recognitio...
متن کاملEntropy based combination of tandem representations for noise robust ASR
In this paper, we present an entropy based method to combine tandem representations of the recently proposed Phase AutoCorrelation (PAC) based features and MelFrequency Cepstral Coefficients (MFCC) features. PAC based features, derived from a nonlinear transformation of autocorrelation coefficients and shown to be noise robust, improve their robustness to additive noise in their tandem represen...
متن کامل