| Περίληψη: | Recently, Automatic Speech Recognition (ASR)
systems were used to assist children in language acquisition as it has
the ability to detect human speech signal. Despite the benefits offered
by the ASR system for children, there is a lack of ASR systems for
Malay-speaking children. One of the contributing factors for this is
the lack of continuous speech database for Malay-speaking children.
Though cross-lingual adaptation is a common solution for developing
ASR systems for under-resourced language, it is not viable for
children as there are very limited children's speech databases as a
source model. In this research, we are proposing a two-stage
adaptation using a very limited database of Malay-speaking children
for the development of the children ASR system. The two stage
adaptation comprises the cross-lingual adaptation (first stage) and
cross-age adaptation. For the first stage, a well-known speech
database that is phonetically rich and balanced, is adapted to the
medium-sized Malay adults using supervised MLLR. The second
stage adaptation uses the speech acoustic model generated from the
first adaptation, and the target database is a small-sized database of
Malay-speaking children. We have measured the performance of the
proposed technique using word error rate, and then compare them
with the conventional benchmark adaptation. The two stage
adaptation proposed in this research has better recognition accuracy
as compared to the benchmark adaptation in recognizing children's
speech.
|
|---|