Search Results for author:
Found 8 papers, 2 papers with code
Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion
We propose an approach for continuous prediction of turn-taking and backchanneling locations in spoken dialogue by fusing a neural acoustic model with a large language model (LLM).
Non-uniform Speaker Disentanglement For Depression Detection From Raw Speech Signals
We find that a greater adversarial weight for the initial layers leads to performance improvement.
Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASR
With the proposed methods (E-APC and DRAFT), the relative WER improvements are even larger (30% and 19% on the OGI and MyST data, respectively) when compared to the models without using pretraining methods.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Unsupervised Instance Discriminative Learning for Depression Detection from Speech Signals
To learn instance-spread-out embeddings, we explore methods for sampling instances for a training batch (distinct speaker-based and random sampling).
A Step Towards Preserving Speakers' Identity While Detecting Depression Via Speaker Disentanglement
With adversarial training, depression classification improves for every feature when compared to the baseline.
VADOI:Voice-Activity-Detection Overlapping Inference For End-to-end Long-form Speech Recognition
Results show that the proposed method can achieve a 20% relative computation cost reduction on Librispeech and Microsoft Speech Language Translation long-form corpus while maintaining the WER performance when comparing to the best performing overlapping inference algorithm.
FrAUG: A Frame Rate Based Data Augmentation Method for Depression Detection from Speech Signals
The improvements for the CONVERGE (Mandarin) dataset when using the x-vector embeddings with CNN as the backend and MFCCs as input features were 9. 32% (validation) and 12. 99% (test).
Low Resource German ASR with Untranscribed Data Spoken by Non-native Children -- INTERSPEECH 2021 Shared Task SPAPL System
~ 5 hours of transcribed data and ~ 60 hours of untranscribed data are provided to develop a German ASR system for children.
