SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.08484 · 2020

Attentron: Few-Shot Text-to-Speech Utilizing Attention-Based Variable-Length Embedding

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
jasminsternkopf/mel_cepstral_distance pwc_unofficial 7 of 8
FunctionStatusWhere it lives
adjust_win_len_to_n_fft Ran jasminsternkopf/mel_cepstral_distance/src/mel_cepstral_distance/computation.py
code served (permissive licence) · get_code("e6f27aedfce3e43f")
amp_to_mag Ran jasminsternkopf/mel_cepstral_distance/src/mel_cepstral_distance/helper.py
code served (permissive licence) · get_code("d79e21a23e4ff79f")
mag_to_energy Ran jasminsternkopf/mel_cepstral_distance/src/mel_cepstral_distance/helper.py
code served (permissive licence) · get_code("6e4093cb3adc644b")
make_cache_key Ran jasminsternkopf/mel_cepstral_distance/experiments/run_experiments.py
code served (permissive licence) · get_code("d506928a11aa3b62")
plot_MC_X_ik Ran jasminsternkopf/mel_cepstral_distance/src/mel_cepstral_distance_analysis/helper.py
code served (permissive licence) · get_code("2f90604feeadcda6")
remove_silence_rms Ran jasminsternkopf/mel_cepstral_distance/src/mel_cepstral_distance/silence.py
code served (permissive licence) · get_code("2b5015c89644558b")
resample_if_necessary Ran jasminsternkopf/mel_cepstral_distance/src/mel_cepstral_distance/helper.py
code served (permissive licence) · get_code("23115e6c5bd95a8e")
load_mos_dataset Not yet run jasminsternkopf/mel_cepstral_distance/experiments/run_experiments.py
code served (permissive licence) · get_code("a1c9a92b090f0829")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

On account of growing demands for personalization, the need for a so-called few-shot TTS system that clones speakers with only a few data is emerging. To address this issue, we propose Attentron, a few-shot TTS model that clones voices of speakers unseen during training. It introduces two special encoders, each serving different purposes. A fine-grained encoder extracts variable-length style information via an attention mechanism, and a coarse-grained encoder greatly stabilizes the speech synthesis, circumventing unintelligible gibberish even for synthesizing speech of unseen speakers. In addition, the model can scale out to an arbitrary number of reference audios to improve the quality of the synthesized speech. According to our experiments, including a human evaluation, the proposed model significantly outperforms state-of-the-art models when generating speech for unseen speakers in terms of speaker similarity and quality.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2005.08484")
get_code_for_paper("2005.08484")
have("2005.08484")

Connect an agent — have() is free.