A review of deep learning techniques for speech processing
The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …
learning. The use of multiple processing layers has enabled the creation of models capable …
Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers
Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is
important to capture the diversity in human speech such as speaker identities, prosodies …
important to capture the diversity in human speech such as speaker identities, prosodies …
Naturalspeech: End-to-end text-to-speech synthesis with human-level quality
Text-to-speech (TTS) has made rapid progress in both academia and industry in recent
years. Some questions naturally arise that whether a TTS system can achieve human-level …
years. Some questions naturally arise that whether a TTS system can achieve human-level …
Adaspeech 4: Adaptive text to speech in zero-shot scenarios
Adaptive text to speech (TTS) can synthesize new voices in zero-shot scenarios efficiently,
by using a well-trained source TTS model without adapting it on the speech data of new …
by using a well-trained source TTS model without adapting it on the speech data of new …
Promptstyle: Controllable style transfer for text-to-speech with natural language descriptions
Style transfer TTS has shown impressive performance in recent years. However, style
control is often restricted to systems built on expressive speech recordings with discrete style …
control is often restricted to systems built on expressive speech recordings with discrete style …
Generation and detection of manipulated multimodal audiovisual content: Advances, trends and open challenges
Generative deep learning techniques have invaded the public discourse recently. Despite
the advantages, the applications to disinformation are concerning as the counter-measures …
the advantages, the applications to disinformation are concerning as the counter-measures …
Delightfultts 2: End-to-end speech synthesis with adversarial vector-quantized auto-encoders
Current text to speech (TTS) systems usually leverage a cascaded acoustic model and
vocoder pipeline with mel-spectrograms as the intermediate representations, which suffer …
vocoder pipeline with mel-spectrograms as the intermediate representations, which suffer …
Low-resource multilingual and zero-shot multispeaker TTS
While neural methods for text-to-speech (TTS) have shown great advances in modeling
multiple speakers, even in zero-shot settings, the amount of data needed for those …
multiple speakers, even in zero-shot settings, the amount of data needed for those …
MSMC-TTS: Multi-stage multi-codebook VQ-VAE based neural TTS
This article aims to improve neural TTS with vector-quantized, compact speech
representations. We propose a Vector-Quantized Variational AutoEncoder (VQ-VAE) based …
representations. We propose a Vector-Quantized Variational AutoEncoder (VQ-VAE) based …
DiCLET-TTS: Diffusion model based cross-lingual emotion transfer for text-to-speech—A study between English and Mandarin
While the performance of cross-lingual TTS based on monolingual corpora has been
significantly improved recently, generating cross-lingual speech still suffers from the foreign …
significantly improved recently, generating cross-lingual speech still suffers from the foreign …