Time shift invariant speech recognition
نویسندگان
چکیده
This paper analyzes the phenomena and illustrates the well known result that classical acoustic front end processors including spectrum and cepstra based techniques su er from timeshift. After describing the e ect of sample sized shifts on the spectral estimates of the signal, we propose several techniques which take advantage of shift variations to multiply the amount of training that speech utterances can provide. Eventually, we illustrate how it is possible to slightly modify the acoustic frontend to render the recognizer invariant to small shifts.
منابع مشابه
The Tdrbf: a Shift Invariant Radial Basis Function Network
| Conventional speech recognition systems based on Multi Layer Percep-trons often use Time Delay Neural Networks (TDNN). TDNNs were rst used for speech recognition by Waibel et al., but long training times and large numbers of parameters that need careful adjustment make it hard to achieve good performance. In contrast, networks using Radial Basis Functions (RBF) can be constructed systematical...
متن کاملPhoneme recognition using ICA-based feature extraction and transformation
We investigate the use of independent component analysis (ICA) for speech feature extraction in speech recognition systems. Although initial research suggested that learning basis functions by ICA for encoding the speech signal in an e5cient manner improved recognition accuracy, we observe that this may be true for a recognition tasks with little training data. However, when compared in a large...
متن کاملTranslation Invariant Approach for Measuring Similarity of Signals
In many signal processing applications, an appropriate measure to compare two signals plays a fundamental role in both implementing the algorithm and evaluating its performance. Several techniques have been introduced in literature as similarity measures. However, the existing measures are often either impractical for some applications or they have unsatisfactory results in some other applicati...
متن کاملTranslation Invariant Approach for Measuring Similarity of Signals
In many signal processing applications, an appropriate measure to compare two signals plays a fundamental role in both implementing the algorithm and evaluating its performance. Several techniques have been introduced in literature as similarity measures. However, the existing measures are often either impractical for some applications or they have unsatisfactory results in some other applicati...
متن کاملUse of spectral centre of gravity for generating speaker invariant features for automatic speech recognition
In this paper, we present an approach to generate speaker invariant features for automatic speech recognition (ASR) using the idea of spectral centre of gravity(CG). This is based on the observation that if two signals are delayed versions of one another, then their CG’s also differ by the same amount. We exploit this idea to appropriately shift the mel warped log compressed spectra using the e...
متن کامل