Audio samples from "Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation"

Abstract: We describe Parrotron, an end-to-end-trained speech-to-speech conversion model that maps an input spectrogram directly to another spectrogram, without utilizing any intermediate discrete representation. The network is composed of an encoder, a spectrogram and phoneme decoders, followed by a vocoder to synthesize a time-domain waveform. We demonstrate that this model can be trained to normalize speech from any speaker regardless of accent, prosody, and background noise, into the voice of a single canonical target speaker with a fixed accent and consistent articulation and prosody. We further show that this normalization model can be adapted to normalize highly atypical speech from a deaf speaker, resulting in significant improvements in intelligibility and naturalness, measured via a speech recognizer and listening tests. Finally, demonstrating the utility of this model on other speech tasks, we show that the same model architecture can be trained to perform a speech separation task.

Note: To obtain the best quality, we strongly recommend readers to listen to the audio samples with headphones.

• Section 3.1: Voice normalization
• Section 3.2: Normalization of hearing-impaired speech
• Section 3.3: Speech separation
• Acknowledgements

Section 3.1: Voice normalization

Input	Output

Examples of running the normalization model, which is trained on American English speech, on non-English inputs.

Section 3.2: Normalization of hearing-impaired speech

 

After adaptation

Input	Output		Reference Transcript
			Here is some information about Oklahoma
			When do the girls get to the party?
			You can use your regular name outside the game.
			Here are listings for Clarks Village near Ann Arbor.
			Maybe something happened to them.
			Amber India restaurant is open until two A M tomorrow.
			Here are your directions.
			OK, three hours 45 minutes.
			What is the weather tomorrow in Mountain View?
			I want to see if Parrotron would work for other languages.
			Salam [Arabic for Peace]
			I like Fadi.
			I'm hungry.

Section 3.3: Speech separation

Input	Output

We thank Françoise Beaufays, Michael Brenner, Diamantino Caseiro, Zhifeng Chen, Mohamed Elfeky, Patrick Nguyen, Bhuvana Ramabhadran, Andrew Rosenberg, Jason Pelecanos, Johan Schalkwyk, Yonghui Wu, and Zelin Wu for useful feedback.