CONF Dines_INTERSPEECH-2_2009/IDIAP Speech recognition with speech synthesis models by marginalising over decision tree leaves Dines, John Saheer, Lakshmi Liang, Hui decision trees speech recognition speech synthesis unified models EXTERNAL https://publications.idiap.ch/attachments/papers/2009/Dines_INTERSPEECH-2_2009.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Dines_Idiap-RR-17-2009 Related documents Proceedings of Interspeech Brighton, U.K. 2009 September 2009 There has been increasing interest in the use of unsupervised adaptation for the personalisation of text-to-speech (TTS) voices, particularly in the context of speech-to-speech translation. This requires that we are able to generate adaptation transforms from the output of an automatic speech recognition (ASR) system. An approach that utilises unified ASR and TTS models would seem to offer an ideal mechanism for the application of unsupervised adaptation to TTS since transforms could be shared between ASR and TTS. Such unified models should use a common set of parameters. A major barrier to such parameter sharing is the use of differing contexts in ASR and TTS. In this paper we propose a simple approach that generates ASR models from a trained set of TTS models by marginalising over the TTS contexts that are not used by ASR. We present preliminary results of our proposed method on a large vocabulary speech recognition task and provide insights into future directions of this work. REPORT Dines_Idiap-RR-17-2009/IDIAP Speech recognition with speech synthesis models by marginalising over decision tree leaves Dines, John Saheer, Lakshmi Liang, Hui EXTERNAL https://publications.idiap.ch/attachments/reports/2009/Dines_Idiap-RR-17-2009.pdf PUBLIC Idiap-RR-17-2009 2009 Idiap July 2009 There has been increasing interest in the use of unsupervised adaptation for the personalisation of text-to-speech (TTS) voices, particularly in the context of speech-to-speech translation. This requires that we are able to generate adaptation transforms from the output of an automatic speech recognition (ASR) system. An approach that utilises unified ASR and TTS models would seem to offer an ideal mechanism for the application of unsupervised adaptation to TTS since transforms could be shared between ASR and TTS. Such unified models should use a common set of parameters. A major barrier to such parameter sharing is the use of differing contexts in ASR and TTS. In this paper we propose a simple approach that generates ASR models from a trained set of TTS models by marginalising over the TTS contexts that are not used by ASR. We present preliminary results of our proposed method on a large vocabulary speech recognition task and provide insights into future directions of this work.