Search Results for author:
Found 10 papers, 0 papers with code
Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control
In this paper, a text-to-rapping/singing system is introduced, which can be adapted to any speaker's voice.
High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency
This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications.
Prosodic Clustering for Phoneme-level Prosody Control in End-to-End Speech Synthesis
This paper presents a method for controlling the prosody at the phoneme level in an autoregressive attention-based text-to-speech system.
Improved Prosodic Clustering for Multispeaker and Speaker-independent Phoneme-level Prosody Control
This paper presents a method for phoneme-level prosody control of F0 and duration on a multispeaker text-to-speech setup, which is based on prosodic clustering.
Self-supervised learning for robust voice cloning
This method enables us to train our model in an unlabeled multispeaker dataset as well as use unseen speaker embeddings to copy a speaker's voice.
Karaoker: Alignment-free singing voice synthesis with speech training data
Existing singing voice synthesis models (SVS) are usually trained on singing data and depend on either error-prone time-alignment and duration features or explicit music score information.
Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation
When used in a cross-lingual setting, acoustic features are initially produced with a native speaker of the target language and then voice conversion is applied by the same model in order to convert these features to the target speaker's voice.
Generating Multilingual Gender-Ambiguous Text-to-Speech Voices
The gender of any voice user interface is a key element of its perceived identity.
Low-Resource Cross-Domain Singing Voice Synthesis via Reduced Self-Supervised Speech Representations
In this paper, we propose a singing voice synthesis model, Karaoker-SSL, that is trained only on text and speech data as a typical multi-speaker acoustic model.
Improved Text Emotion Prediction Using Combined Valence and Arousal Ordinal Classification
We thus redefine the emotion labeling problem by shifting it from a traditional classification model to an ordinal classification one, where discrete emotions are arranged in a sequential order according to their valence levels.
