Research
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

13263952 · Nov 201919922001200920182026
48 results for Japanese speech synthesis

Enhanced Tacotron for Japanese speech synthesis improves naturalness.

problem Challenges in end-to-end Japanese speech synthesis due to pitch accents.
method Extended Tacotron with self-attention to capture pitch accent dependencies.
result Proposed systems show improvements but still lag behind traditional pipeline methods.

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.

Proposes DNN-based speaker embedding correlated with subjective inter-speaker similarity for speech synthesis.

problem Inadequate speaker representation for open speakers not in training data.
method Two training algorithms using inter-speaker similarity matrices: similarity vector embedding and similarity matrix embedding.
result Proposed algorithms learn speaker embedding highly correlated with subjective inter-speaker similarity.

WaveCycleGAN2 improves speech synthesis quality by reducing aliasing.

problem Human ear can still distinguish synthesized speech from natural speech.
method WaveCycleGAN2 uses generators without down/up-sampling modules and combines discriminators from waveform and acoustic parameter domains.
result WaveCycleGAN2 achieves high-quality speech synthesis with comparable mean opinion scores to natural speech.

Improved visual speech synthesis using adapted ASR acoustic models.

problem Lack of synchronized audio, video, and depth data for speaker-independent speech-driven visual speech synthesis.
method Adapted an ASR acoustic model trained on audio-only data to the visual speech synthesis domain.
result Viewers significantly prefer animations generated from the adapted ASR acoustic model.

This study improves text-to-speech synthesis using GANs for glottal excitation.

problem Slow inference and computational cost of WaveNet and difficulty in parallel training of GANs.
method Adopted GANs for parallel waveform generation in speech signal and glottal excitation.
result GAN-based glottal excitation model achieves quality and voice similarity on par with WaveNet.

A new TTS method uses diffusion and VAE for better speech synthesis.

problem Improving text-to-speech synthesis for better speech quality and robustness.
method Combines diffusion probabilistic model and variational autoencoder for latent variable conversion.
result The method is robust to poor orthography and alignment errors.

RUSLAN is a large Russian speech corpus for text-to-speech.

problem Lack of high-quality annotated Russian speech data for text-to-speech.
method Developed a large annotated Russian speech corpus and trained a neural network for text-to-speech synthesis.
result Synthesized speech quality evaluated with MOS scores: 4.05 for naturalness, 3.78 for intelligibility.

This research improves neural synthesizers for music sounds from speech data.

problem Applying speech synthesis techniques to musical instrument sounds.
method Comparison of three neural synthesizers in three scenarios: training, zero-shot learning, and fine-tuning.
result Neural synthesizers trained on speech data and fine-tuned on music data perform better.

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.

RawNet synthesizes speech without relying on human-designed features.

problem Speech synthesis models rely heavily on human-designed spectral features.
method End-to-end neural vocoder using auto-encoder structure, learning features and audio recovery directly from raw waveform.
result RawNet achieves better speech quality with a simplified model architecture and faster inference speed.

Speech Translation has always been about giving source text or audio input and waiting for system to give translated output in desired form. In this paper, we present the Acoustic Dialect Decoder (ADD) - a voice to voice ear-piece translation device. We introduce and survey the recent advances made in the field of Spee…

2016-10-13abs ↗pdf ↗

PriorGrad improves speech synthesis models by using data-dependent adaptive priors.

problem Inefficiency in denoising diffusion models due to mismatch between prior and data distributions.
method Proposes PriorGrad, an adaptive prior derived from data statistics based on conditional information.
result PriorGrad achieves faster convergence and superior performance in speech synthesis models.

Non-autoregressive transformer improves speech recognition speed and accuracy.

problem Reducing inference computation cost in speech recognition.
method Two non-autoregressive transformer structures (A-CMLM and A-FMLM) trained with masked tokens and iterative prediction during inference.
result Non-autoregressive transformer can match autoregressive transformer performance with 7x speedup.

Polynomial fusion layer improves speech-driven facial animation.

problem Recent facial synthesis relies on low-dimensional representations and concatenation, ignoring higher-order interactions.
method Proposes a polynomial fusion layer to model higher-order interactions of facial encodings.
result Demonstrates improved video quality, audiovisual synchronisation, and blink generation.

Speech enhancement improved by adapting to unknown speakers without auxiliary signals.

problem Improving speech enhancement accuracy for unknown speakers.
method Adopting multi-task learning for speech enhancement and speaker identification, using multi-head self-attention.
result Achieved state-of-the-art performance and improved subjective quality.

Generative models produce varied intonation in speech synthesis.

problem Typical TTS systems lack the ability to produce multiple distinct renditions of a sentence.
method Use variational autoencoders (VAEs) to capture a distribution over multiple renditions and produce varied intonation.
result Sampling from the tails of the VAE prior produces more varied intonation than traditional approaches, while maintaining naturalness.

Attention forcing improves sequence-to-sequence model training stability.

problem Training auto-regressive sequence-to-sequence models with attention mechanism is challenging.
method Attention forcing guides the model with generated output history and reference attention.
result Attention forcing trains models to recover from mistakes without requiring a schedule or classifier.

Improves text-to-speech speed by interleaving character reading and audio synthesis.

problem Latency in text-to-speech models limits their use in time-sensitive tasks.
method Reinforcement learning to train an agent to choose the order of character reading and audio synthesis.
result The proposed method successfully balances latency and audio quality.

Unsupervised model generates distinct intonation codes for speech synthesis.

problem Lack of understanding of what prosodic variations are controlled in speech synthesis.
method Phrase-level variational autoencoder with multi-modal prior, using mode centres as intonation codes.
result Generated intonation codes are perceptually distinct and carry various affect-related styles.

Detects AI-synthesized speech using cepstral and bispectral analysis.

problem Validating the authenticity of speech from AI-generated content.
method Integrates cepstral and bispectral analysis for distinguishing human from AI-synthesized speech.
result Higher-order statistics show less correlation for human speech compared to AI-synthesis, and cepstral analysis reveals unique power components.

Deep learning models improve sound separation across various types of sounds.

problem Developing a universal method to separate arbitrary sounds of different types.
method Created a dataset of mixtures containing arbitrary sounds, investigated mask-based separation architectures, and tested different framewise analysis-synthesis bases.
result STFT outperformed learnable bases in universal sound separation tasks.

NSF models generate speech waveforms faster and better than WaveNet.

problem Efficiently generating speech waveforms for statistical parametric synthesis.
method Neural source-filter (NSF) models that combine sine-based excitation, non-AR filter, and conditional preprocessing.
result NSF models generate waveforms 100 times faster than WaveNet and have better quality.

iSTFTNet speeds up mel-spectrogram vocoders without sacrificing quality.

problem Efficiently converting mel-spectrograms to speech with minimal computation.
method Replaces convolutional layers with iSTFT after frequency dimension reduction.
result Significant reduction in computational cost with comparable quality.

This research investigates the Statistical Machine Translation approaches to translate speech in real time automatically. Such systems can be used in a pipeline with speech recognition and synthesis software in order to produce a real-time voice communication system between foreigners. We obtained three main data sets …

2015-09-30abs ↗pdf ↗