Recently, Google launched YouTube Kids, a mobile application for children, that uses a speech recognizer built specifically for recognizing children's speech. In this paper we present techniques we explored to build such a system. We describe the use of a neural network classifier to identify matched acoustic training data, filtering data for language modeling to reduce the chance of producing offensive results. We also compare long short-term memory (LSTM) recurrent networks to convolutional, LSTM, deep neural networks (CLDNN). We found that a CLDNN acoustic model outperforms an LSTM across a variety of different conditions, but does not specifically model child speech relatively better than adult. Overall, these findings allow us to build a successful, state-of-the-art large vocabulary speech recognizer for both children and adults.
Bibliographic reference. Liao, Hank / Pundak, Golan / Siohan, Olivier / Carroll, Melissa K. / Coccaro, Noah / Jiang, Qi-Ming / Sainath, Tara N. / Senior, Andrew / Beaufays, Françoise / Bacchiani, Michiel (2015): "Large vocabulary automatic speech recognition for children", In INTERSPEECH-2015, 1611-1615.