Search Results for author:
Found 7 papers, 0 papers with code
Stylebook: Content-Dependent Speaking Style Modeling for Any-to-Any Voice Conversion using Only Speech Data
Finally, content information extracted from the source speech and content-dependent target style embeddings are fed into a diffusion-based decoder to generate the converted speech mel-spectrogram.
Parameter Efficient Audio Captioning With Faithful Guidance Using Audio-text Shared Latent Representation
Then, we propose a parameter efficient inference time faithful decoding algorithm that enables smaller audio captioning models with performance equivalent to larger models trained with more data.
Improved Beam Search for Hallucination Mitigation in Abstractive Summarization
In this paper, we investigate the use of the Natural Language Inference (NLI) entailment metric to detect and prevent hallucinations in summary generation.
Application of Knowledge Distillation to Multi-task Speech Representation Learning
Model architectures such as wav2vec 2. 0 and HuBERT have been proposed to learn speech representations from audio waveforms in a self-supervised manner.
Activity report analysis with automatic single or multispan answer extraction
Depending on the context and the type of question asked, a question answering (QA) system would need to automatically determine whether the answer covers single-span or multi-span text components.
Multi-task Voice Activated Framework using Self-supervised Learning
Finally, we extend our framework to perform multi-task learning by jointly optimizing the network parameters on multiple voice activated tasks using a shared transformer backbone.
Ranked #6 on
Speaker Verification
on VoxCeleb
Incremental Learning Algorithm for Sound Event Detection
The neural adapter layer facilitates the target model to learn new sound events with minimal training data and maintaining the performance of the previously learned sound events similar to the source model.
