Auditory Effects for ASR
نویسنده
چکیده
Almost all ASR front ends use an amplitude-independent representation of spectral shape as the primary feature vector, obtained via some combination of normalization, logarithms, or AR modeling. They also typically represent total power or loudness as a separate feature. These ideas are fine to first order, and have gotten ASR to where it is today. But they totally punt on the issue of what is "loud enough".
منابع مشابه
Pitch-Synchronous Peak-Amplitude (PS-PA)-Based Feature Extraction Method for Noise-Robust ASR
A novel pitch-synchronous auditory-based feature extraction method for robust automatic speech recognition (ASR) is proposed. A pitch-synchronous zero-crossing peak-amplitude (PS-ZCPA)-based feature extraction method was proposed previously and it showed improved performances except when modulation enhancement was integrated with Wiener filter (WF)-based noise reduction and auditory masking. Ho...
متن کاملSensory gating in rats: lack of correlation between auditory evoked potential gating and prepulse inhibition.
This study was designed to evaluate the possible similarities between two paradigms designed to measure sensory gating: (1) an auditory evoked potential (AEP), called the P50 gating paradigm; and (2) an acoustic startle (ASR), called the prepulse inhibition paradigm. These paradigms show a number of methodological, pharmacological, and neurobiological similarities, and they are both disturbed i...
متن کاملA psychoacoustical model of the auditory periphery as front end for ASR
The application of a psychoacoustical model of the auditory periphery in the field of automatic speech recognition (ASR) is presented. The model was developed to quantitatively predict human performance in typical spectral and temporal masking experiments. Speaker-independent, isolated-digit recognition experiments in different types of noise were carried out to evaluate the robustness of the a...
متن کاملWhy do ASR Systems Despite Neural Nets Still Depend on Robust Features
To which extent can neural nets learn traditional signal processing stages of current robust ASR front-ends? Will neural nets replace the classical, often auditory-inspired feature extraction in the near future? To answer these questions, a DNN-based ASR system was trained and tested on the Aurora4 robust ASR task using various (intermediate) processing stages. Additionally, the training set wa...
متن کاملHow does the integration of speech recognition controls and spatialized auditory displays affect user workload?
The purpose of this study was to determine the effects of the integration of automatic speech recognition (ASR) controls and spatial audio displays on soldier workload in noisy, cognitively demanding environments such as armored vehicles. To achieve this end, measures of mental workload were obtained in tasks in which subjects were instructed to give ASR voice commands in response to simulated ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1996