1 |
Differences in counting skills between Chinese and German children are accompanied by differences in processing of approximate numerical magnitude information
|
|
|
|
In: Frontiers in psychology 9 (2019), 8 S. (2019)
|
|
BASE
|
|
Show details
|
|
2 |
Differences in Counting Skills Between Chinese and German Children Are Accompanied by Differences in Processing of Approximate Numerical Magnitude Information
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Differences in Counting Skills Between Chinese and German Children Are Accompanied by Differences in Processing of Approximate Numerical Magnitude Information
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Do Preschool Children Learn to Read Words from Environmental Prints?
|
|
|
|
BASE
|
|
Show details
|
|
5 |
CASA Based Speech Separation for Robust Speech Recognition
|
|
|
|
In: http://www.dcs.shef.ac.uk/~martin/SpeechSeparationChallenge/han.pdf
|
|
Abstract:
This paper introduces a speech separation system which is used as a front-end processing step for automatic speech recognition (ASR). It is designed based on computational auditory scene analysis (CASA) to separate the target speech from the interference speech. Firstly, the mixed speech is preprocessed based on auditory peripheral model. Secondly, pitch tracking is conducted and the dominant pitch is used as a main cue to find the target speech. Thirdly, the time frequency (TF) units are merged into many segments, which are combined into streams in CASA initial grouping step. And then a regrouping strategy is employed to refine those streams via amplitude modulate (AM) cues, which are finally organized by the speaker recognition techniques into corresponding speakers. At last, the output streams will be reconstructed to compensate the missing data in the abovementioned processing steps by a cluster based feature reconstruction. The experimental results of ASR show that to the speech with high TMR (>-6dB), the system does not perform well, and to the low TMR (<-6dB) the recognition accuracy of processed speech is higher than that of unprocessed speech. 1.
|
|
URL: http://www.dcs.shef.ac.uk/~martin/SpeechSeparationChallenge/han.pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.136.6579
|
|
BASE
|
|
Hide details
|
|
|
|