Learning singing from speech

A computer system for converting a singing voice of a first person to a singing voice of a second person using a speaking voice of the second person, the computer system comprising:

• one or more computer-readable non-transitory storage media configured to store computer program code;
• and
• one or more computer processors configured to access said computer program code and operate as instructed by said computer program code, said computer program code including:
• encoding code configured to cause the one or more computer processors to encode a context associated with one or more phonemes corresponding to the singing voice of a first person;
• aligning code configured to cause the one or more computer processors to align the one or more phonemes to one or more target acoustic frames based on the encoded context, wherein the aligning code further causes the one or more computer processors to:
• concatenate an output sequence of hidden states with information corresponding to the singing voice of a first person;
• apply dimension reduction to the concatenated output sequence using a fully connected layer;
• expand the dimension-reduced output sequence based on a duration associated with each phoneme;
• and
• align the expanded output sequence to the target acoustic frames;
• generating code configured to cause the one or more computer processors to, generate one or more mel-spectrogram features based on a neural network model jointly trained using speaker embeddings that are a representation of embeddings for singing and speaking, wherein the one or more mel-spectrogram features are generated from the aligned phonemes, the target acoustic frames, and a sample of the speaking voice of the second person;
• and
• converting code configured to cause the one or more computer processors to convert a sample corresponding to the singing voice of a first person to a sample corresponding to the second singing voice using the generated mel-spectrogram features.

A non-transitory computer readable medium having stored thereon a computer program for converting a singing voice of a first person to a singing voice of a second person using a speaking voice of the second person, the computer program configured to cause one or more computer processors to:

• encode a context associated with one or more phonemes corresponding to the singing voice of a first person;
• align the one or more phonemes to one or more target acoustic frames based on the encoded context, the aligning comprising:
• concatenating an output sequence of hidden states with information corresponding to the singing voice of a first person;
• applying dimension reduction to the concatenated output sequence using a fully connected layer;
• expanding the dimension-reduced output sequence based on a duration associated with each phoneme;
• and
• aligning the expanded output sequence to the target acoustic frames;
• recursively generate one or more mel-spectrogram features based on a neural network model jointly trained using speaker embeddings that are a representation of embeddings for singing and speaking, wherein the one or more mel-spectrogram features are generated from the aligned phonemes, the target acoustic frames, and a sample of the speaking voice of the second person;
• and
• convert a sample corresponding to the singing voice of a first person to a sample corresponding to the second singing voice using the generated mel-spectrogram features.