Automatic Detection of Emphasized Words for Performance Enhancement of a Czech ASR System
نویسنده
چکیده
This paper deals with a problem of prosodically emphasized word detection in Czech speech. The main goal is to propose an automatic emphasized word detection system that would be component of an Automatic speech recognition system (ASR) and would enrich its text output with highlighting emphasized words. The detection method is based on Czech prosodic rules and uses speech signal intensity, pitch (fundamental frequency) and speech segment duration as features. A large speech corpus has been used to compute some prosodic statistics, which have been designated for feature evaluation. The proposed system is speaker-independent and it achieves a detection score of 91%.
منابع مشابه
Stacked auto-encoder for ASR error detection and word error rate prediction
Recently, Stacked Auto-Encoders (SAE) have been successfully used for learning imbalanced datasets. In this paper, for the first time, we propose to use a Neural Network classifier furnished by an SAE structure for detecting the errors made by a strong Automatic Speech Recognition (ASR) system. Error detection on an automatic transcription provided by a ”strong” ASR system, i.e. exhibiting a sm...
متن کاملOut-of-Vocabulary Word Detection and Beyond
In this work, we summarize our experiences in detection of unexpected words in automatic speech recognition (ASR). Two approaches based upon a paradigm of incongruence detection between generic and specific recognition systems are introduced. By arguing, that detection of incongruence is a necessity, but does not suffice when having in mind possible follow-up actions, we motivate the preference...
متن کاملDimensionality Reduction and Improving the Performance of Automatic Modulation Classification using Genetic Programming (RESEARCH NOTE)
This paper shows how we can make advantage of using genetic programming in selection of suitable features for automatic modulation recognition. Automatic modulation recognition is one of the essential components of modern receivers. In this regard, selection of suitable features may significantly affect the performance of the process. Simulations were conducted with 5db and 10db SNRs. Test and ...
متن کاملFuzzy Neighbor Voting for Automatic Image Annotation
With quick development of digital images and the availability of imaging tools, massive amounts of images are created. Therefore, efficient management and suitable retrieval, especially by computers, is one of themost challenging fields in image processing. Automatic image annotation (AIA) or refers to attaching words, keywords or comments to an image or to a selected part of it. In this paper,...
متن کاملExperiments with an extended adaptive SVD enhancement scheme for speech recognition in noise
An extension to adaptive signal subspace methods is presented, based on singular value decomposition (SVD) with an online estimation of the noise variance. With this approach aiming at automatic speech recognition (ASR) in adverse environmental conditions no speech detection has to be performed. A comparison of different SVD approaches and nonlinear spectral subtraction within ASR experiments o...
متن کامل