Abstract | ||
---|---|---|
For a connected digits speech recognition task, we have com- pared the performance of two inexpensive electret microphones with that of a single high quality PZM microphone. Recogni- tion error rates were measured both with and without compen- sation techniques, where both single-channel and two-channel approaches were used. In all cases the task was recognition at a significant distance (2-6 feet) from the talker' s mouth. The re- sults suggest that the wide variability in characteristics among inexpensive electret microphones can be compensated for with- out explicit quality control, and that this is particularly effec- tive when both single-channel and two-channel techniques are used. In particular, the resulting performance for the inexpen- sive microphones used together is essentially equivalent to the expensive microphone, and better than for either inexpensive microphone used alone. |
Year | Venue | Keywords |
---|---|---|
2003 | INTERSPEECH | speech recognition,error rate,quality control |
DocType | Citations | PageRank |
Conference | 2 | 0.76 |
References | Authors | |
6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Laura Docío Fernández | 1 | 83 | 18.72 |
David Gelbart | 2 | 134 | 17.54 |
Nelson Morgan | 3 | 3048 | 533.52 |