Yanwei Pan
YOU?
Author Swipe
View article: Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition
Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition Open
End-to-end models have achieved state-of-the-art results on several automatic speech recognition tasks. However, they perform poorly when evaluated on long-form data, e.g., minutes long conversational telephony audio. One reason the model …
View article: Input Length Matters: An Empirical Study Of RNN-T And MWER Training For Long-form Telephony Speech Recognition.
Input Length Matters: An Empirical Study Of RNN-T And MWER Training For Long-form Telephony Speech Recognition. Open
End-to-end models have achieved state-of-the-art results on several automatic speech recognition tasks. However, they perform poorly when evaluated on long-form data, e.g., minutes long conversational telephony audio. One reason the model …