Search Results for author:
Found 6 papers, 1 papers with code
When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection
In addition, this approach is not only valuable for the detection of depression but also represents a new perspective in enhancing the ability of LLMs to comprehend and process speech signals.
Phonological Level wav2vec2-based Mispronunciation Detection and Diagnosis Method
We further propose a multi-label variant of the Connectionist Temporal Classification (CTC) approach to jointly model the non-mutually exclusive speech attributes using a single model.
Spatial HuBERT: Self-supervised Spatial Speech Representation Learning for a Single Talker from Multi-channel Audio
Spatial HuBERT learns representations that outperform state-of-the-art single-channel speech representations on a variety of spatial downstream tasks, particularly in reverberant and noisy environments.
Variational Connectionist Temporal Classification for Order-Preserving Sequence Modeling
Connectionist temporal classification (CTC) is commonly adopted for sequence modeling tasks like speech recognition, where it is necessary to preserve order between the input and target sequences.
Improving Children's Speech Recognition by Fine-tuning Self-supervised Adult Speech Representations
We assess the performance of fine-tuning on both native and non-native children's speech, examine the effect of cross-domain child corpora, and investigate the minimum amount of child speech required to fine-tune a model which outperforms a state-of-the-art adult model.
Speaker- and Age-Invariant Training for Child Acoustic Modeling Using Adversarial Multi-Task Learning
These high acoustic variations along with the scarcity of child speech corpora have impeded the development of a reliable speech recognition system for children.
