6 papers
Prompt-Consistency Inference for Zero-Shot Flow-Matching Text-to-Speech Models
Vasily Zadorozhnyy, Can Goksen, Kazuhito Koishida +1
In recent years, flow-matching models have produced significant improvements in zero-shot text-to-speech synthesis. Conditioned on an audio prompt and text, these models learn a ve…
Zero-Shot Text-to-Speech from Continuous Text Streams
Trung Dang, David Aponte, Dung Tran +2
Existing zero-shot text-to-speech (TTS) systems are typically designed to process complete sentences and are constrained by the maximum duration for which they have been trained. H…
LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes
Trung Dang, David Aponte, Dung Tran +1
Prior works have demonstrated zero-shot text-to-speech by using a generative language model on audio tokens obtained via a neural audio codec. It is still challenging, however, to…
uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures
Afrina Tabassum, Dung Tran, Trung Dang +2
Masked Autoencoders (MAEs) learn rich low-level representations from unlabeled data but require substantial labeled data to effectively adapt to downstream tasks. Conversely, Insta…
Learned Image Compression with Text Quality Enhancement
Chih-Yu Lai, Dung Tran, Kazuhito Koishida
Learned image compression has gained widespread popularity for their efficiency in achieving ultra-low bit-rates. Yet, images containing substantial textual content, particularly s…
ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation
Yatong Bai, Trung Dang, Dung Tran +2
Diffusion models are instrumental in text-to-audio (TTA) generation. Unfortunately, they suffer from slow inference due to an excessive number of queries to the underlying denoisin…