Phone-discriminating minimum classification error (p-MCE) training for phonetic recognition
By Qian Qian, Xiaodong He, Li Deng. 2007
19 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Dong Yu
- Tara N. Sainath
- Bhuvana Ramabhadran
- Jinyu Li
- Michael A. Picheny
- Li Deng
- David Nahamoo
- Dimitri Kanevsky
In Signal Processing
- Tara N. Sainath
- Dong Yu
- Bhuvana Ramabhadran
- Michael A. Picheny
- Jinyu Li
- David Nahamoo
- Dimitri Kanevsky
- Li Deng
Citations in the corpus
- Exemplar-Based Sparse Representation Features: From TIMIT to LVCSR (2011, result): “We also explored the MPE criterion, though the objective function appeared sensitive to the phone accuracy counts for phonetic recognition and therefore little gain was found. Similar results were also observed in [ 5 ].”
- Machine Learning Paradigms for Speech Recognition: An Overview (2013, unknown): “They include: 1)MMI [101], [121]; 2)MCE, which can be interpreted as minimal sentence error rate [79] or approximate minimal phone error rate [122]; 3) MPE or minimal phone error [73], [123]; and 4) MWE or minimal word error.”