Philosophy

Timbre

Operating system

Intelligibility (philosophy)

Economics

Set (abstract data type)

Computer science

Visual arts

Computer network

Musical

Task (project management)

Spectrogram

Management

Epistemology

Speech processing

Singing

Synchronization (alternating current)

Artificial intelligence

Programming language

Channel (broadcasting)

Encoder

Speech recognition

In this paper our goal is to convert a set of spoken lines into sung ones. Unlike previous signal processing based methods, we take a learning based approach to the problem. This allows us to automatically model various aspects of this transformation, thus overcoming dependence on specific inputs such as high quality singing templates or phoneme-score synchronization information. Specifically, we propose an encoder-decoder framework for our task. Given time-frequency representations of speech and a target melody contour, we learn encodings that enable us to synthesize singing that preserves the linguistic content and timbre of the speaker while adhering to the target melody. We also propose a multi-task learning based objective to improve lyric intelligibility. We present a quantitative and qualitative analysis of our framework.

Speech-To-Singing Conversion in an Encoder-Decoder Framework