- Sliding window of fixed length is used to generate individual pronunciations for each input letter
| _ | _ | m | a | t | m | |
| _ | m | a | t | t | @ | |
| m | a | t | t | _ | t | |
| a | t | t | _ | _ | _ |
- Each context sequence is used as a training sample
| _ | _ | m | a | t | m | |
| _ | m | a | t | t | @ | |
| m | a | t | t | _ | t | |
| a | t | t | _ | _ | _ |