Papers › Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch...

Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens

26 Oct 2019arXiv:1910.11997archive 2025-07-28

Rafael Valle, Jason Li, Ryan Prenger, Bryan Catanzaro

Mellotron is a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data. By explicitly conditioning on rhythm and continuous pitch contours from an audio signal or music score, Mellotron is able to generate speech in a variety of styles ranging from read speech to expressive speech, from slow drawls to rap and from monotonous voice to singing voice. Unlike other methods, we train Mellotron using only read speech data without alignments between text and audio. We evaluate our models using the LJSpeech and LibriTTS datasets. We provide F0 Frame Errors and synthesized samples that include style transfer from other speakers, singers and styles not seen during training, procedural manipulation of rhythm and pitch and choir synthesis.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

NVIDIA/mellotron mentioned on GitHubpytorchSyntology: not harvested report
ai-unicamp/tts-objective-metrics mentioned on GitHubpytorchSyntology: not harvested report
deterministic-algorithms-lab/Speech-Explorations mentioned on GitHubpytorchSyntology: not harvested report
ucsd-dsc-arts/dsc160-final-dsc160-final-group14 mentioned on GitHubpytorchSyntology: not harvested report
keonlee9420/Comprehensive-Tacotron2 pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings (arXiv:1910.10838; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

RhythmStyle Transfer

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BiLSTMDilated Causal ConvolutionLSTMLinear LayerLocation Sensitive AttentionMixture of Logistic DistributionsTacotron 2WaveNetZoneout

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections