Search Results for author:
Found 12 papers, 1 papers with code
An analysis of large speech models-based representations for speech emotion recognition
Large speech models-derived features have recently shown increased performance over signal-based features across multiple downstream tasks, even when the networks are not finetuned towards the target task.
Towards generalisable and calibrated synthetic speech detection with self-supervised representations
Generalisation -- the ability of a model to perform well on unseen data -- is crucial for building reliable deep fake detectors.
An analysis on the effects of speaker embedding choice in non auto-regressive TTS
In this paper we introduce a first attempt on understanding how a non-autoregressive factorised multi-speaker speech synthesis architecture exploits the information present in different speaker embedding sets.
Residual Information in Deep Speaker Embedding Architectures
This means that the embeddings are far from ideal, highly dependent on the training corpus and still include a degree of residual information pertaining to factors such as linguistic content, recording conditions or speaking style of the utterance.
The ZevoMOS entry to VoiceMOS Challenge 2022
This paper introduces the ZevoMOS entry to the main track of the VoiceMOS Challenge 2022.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
FlexLip: A Controllable Text-to-Lip System
This modularity enables the easy replacement of each of its components, while also ensuring the fast adaptation to new speaker identities by disentangling or projecting the input features.
Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis
Building multispeaker neural network-based text-to-speech synthesis systems commonly relies on the availability of large amounts of high quality recordings from each speaker and conditioning the training process on the speaker's identity or on a learned representation of it.
An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis
The visualisation of the t-SNE projections of the natural and synthesised speaker embeddings show that the acoustic model shifts some of the speakers' neural representation, but not all of them.
Speaker disentanglement in video-to-speech conversion
The task of video-to-speech aims to translate silent video of lip movement to its corresponding audio signal.
An evaluation of word-level confidence estimation for end-to-end automatic speech recognition
In this paper we investigate confidence estimation for end-to-end automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
RECOApy: Data recording, pre-processing and phonetic transcription for end-to-end speech-based applications
RECOApy streamlines the steps of data recording and pre-processing required in end-to-end speech-based applications.
RSS-TOBI - A Prosodically Enhanced Romanian Speech Corpus
This paper introduces a recent development of a Romanian Speech corpus to include prosodic annotations of the speech data in the form of ToBI labels.
