The langid
module identifies languages in language identification feature data.
The langid
module has three modes of operation.
Mode | Input | Output | Description |
---|---|---|---|
BOUNDARY
|
lf
|
lid , lb |
Identifies the boundaries where the spoken language changes and identifies the language for sections between boundaries. |
CUMULATIVE
|
lf
|
lid
|
Returns the identification score at periodic intervals. |
SEGMENTED
|
lf
|
lif
|
The audio is split into fixed-size chunks and a language is identified for each chunk. |
Examples:
lid ← langid(SEGMENTED, lf)
lid ← langid(CUMULATIVE, lf)
lid, lb ← langid(BOUNDARY, lf)
Some of these parameters do not have an internal default value. You must either set the configuration parameter to a suitable value, or set the value in the corresponding action parameter.
|