Almost all current automatic speech recognition (ASR) systems conventionally append delta and double-delta cepstral features to static cepstral features. In this work we describe ...
Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approa...
Lukas Burget, Petr Schwarz, Mohit Agarwal, Pinar A...
This paper investigates the impact of subspace based techniques for acoustic modeling in automatic speech recognition (ASR). There are many well known approaches to subspace based...
This paper presents a noise estimation technique based on knowledge of pitch information for robust speech recognition. In the first stage the noise is estimated by means of extr...
Juan Andres Morales-Cordovilla, Ning Ma, Victoria ...
Language models for speech recognition tend to be brittle across domains, since their performance is vulnerable to changes in the genre or topic of the text on which they are trai...