Voice2Series:ReprogrammingAcousticModelsforTimeSeriesClassificationChao-HanHuckYang1Yun-YunTsai2Pin-YuChen3AbstracttargetreprogrammedsourceoutputtargetoutputLearningtoclassifytimeserieswithlimitedd...
FusedAcousticandTextEncodingforMultimodalBilingualPretrainingandSpeechTranslationRenjieZheng1JunkunChen2MingboMa1LiangHuang12AbstractSpeechAbundantScarceTranscriptionRecently,representationlearning...