On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “Tacotron”

Joint training framework for text-to-speech and voice conversion using multi-source Tacotron and WaveNeteess.AS

Joint training model for TTS and VC tasks using Tacotron and WaveNet.

problem Training a shared model for text-to-speech and voice conversion.

method Extended Tacotron model with dual attention mechanism for shared tasks, WaveNet for waveform generation.

result Joint training of a shared model achieves both TTS and VC tasks efficiently.

text-to-speech voice conversion Tacotron WaveNet multi-source

2019-03-29abs ↗pdf ↗

Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesiscs.CL

Global Style Tokens (GSTs) are a recently-proposed method to learn latent disentangled representations of high-dimensional data. GSTs can be used within Tacotron, a state-of-the-art end-to-end text-to-speech synthesis system, to uncover expressive factors of variation in speaking style. In this work, we introduce the T…

2018-08-04abs ↗pdf ↗

Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent languageeess.AS

End-to-end speech synthesis is a promising approach that directly converts raw text to speech. Although it was shown that Tacotron2 outperforms classical pipeline systems with regards to naturalness in English, its applicability to other languages is still unknown. Japanese could be one of the most difficult languages …

2018-10-29abs ↗pdf ↗

Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesiseess.AS

Investigates neural TTS systems for Japanese and English.

problem Improving neural TTS systems for high-quality speech synthesis.

method Comparative study of neural sequence-to-sequence TTS vs. DNN pipeline TTS, varying model architecture, parameter size, and language.

result A neural sequence-to-sequence TTS system requires sufficient model parameters and a powerful encoder for high-quality speech synthesis.

neural TTS sequence-to-sequence text-to-speech Japanese English

2020-05-20abs ↗pdf ↗

Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesiseess.AS

Paper proposes a new model for speech synthesis with better interpretability.

problem Improving interpretability in speech synthesis models.

method Hierarchical, fine-grained latent variable model with conditional variational auto-encoder (VAE).

result The new model allows better interpretability without degrading performance.

speech synthesis prosody modeling interpretability VAE hierarchical structure

2020-02-06abs ↗pdf ↗

Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noiseeess.AS

Telephonetic improves robustness of neural language models to ASR errors.

problem Handling ASR errors and semantic noise in neural language models trained on written text.

method Data augmentation framework using character-level and embedding space perturbations.

result Achieves state-of-the-art perplexity of 37.49 on Penn Treebank corpus.

Speech-to-Text Text-to-Speech Language Models Data Augmentation ASR Errors

2019-06-13abs ↗pdf ↗